diff --git a/studio/backend/colab.py b/studio/backend/colab.py
index 7162b6d4c2..f2f56b7f17 100644
--- a/studio/backend/colab.py
+++ b/studio/backend/colab.py
@@ -9,6 +9,32 @@ Uses Colab's built-in proxy - no external tunneling needed!
 from pathlib import Path
 import sys
 
+
+def _bootstrap_studio_venv() -> None:
+    """Expose the Studio venv's site-packages to the current interpreter.
+
+    On Colab, notebook cells run outside the venv subshell. Instead of
+    installing the full stack into system Python, we prepend the venv's
+    site-packages so that packages like structlog, fastapi, etc. are
+    importable from notebook cells and take priority over system copies.
+    """
+    venv_lib = Path.home() / ".unsloth" / "studio" / ".venv" / "lib"
+    if not venv_lib.exists():
+        import warnings
+
+        warnings.warn(
+            f"Studio venv not found at {venv_lib.parent} -- run 'unsloth studio setup' first",
+            stacklevel = 2,
+        )
+        return
+    for sp in venv_lib.glob("python*/site-packages"):
+        sp_str = str(sp)
+        if sp_str not in sys.path:
+            sys.path.insert(0, sp_str)
+
+
+_bootstrap_studio_venv()
+
 # Add backend to path early so local modules like loggers can be imported
 backend_path = str(Path(__file__).parent)
 if backend_path not in sys.path:
diff --git a/studio/backend/core/__init__.py b/studio/backend/core/__init__.py
index 051f6615a7..d8d95e2f1a 100644
--- a/studio/backend/core/__init__.py
+++ b/studio/backend/core/__init__.py
@@ -10,6 +10,16 @@ like unsloth, transformers, or torch before the version activation
 code has a chance to run.
 """
 
+import sys
+from pathlib import Path
+
+# Ensure the backend directory is on sys.path so that bare "from utils.*"
+# imports used throughout the backend work when core is imported as a package
+# (e.g. from the CLI: "from studio.backend.core import ModelConfig").
+_backend_dir = str(Path(__file__).resolve().parent.parent)
+if _backend_dir not in sys.path:
+    sys.path.insert(0, _backend_dir)
+
 __all__ = [
     # Inference
     "InferenceBackend",
diff --git a/studio/backend/core/export/worker.py b/studio/backend/core/export/worker.py
index 4f74f662ee..6af6ff1193 100644
--- a/studio/backend/core/export/worker.py
+++ b/studio/backend/core/export/worker.py
@@ -40,59 +40,25 @@ def _activate_transformers_version(model_name: str) -> None:
     if backend_path not in sys.path:
         sys.path.insert(0, backend_path)
 
-    from utils.transformers_version import needs_transformers_5, _resolve_base_model
+    from utils.transformers_version import (
+        needs_transformers_5,
+        _resolve_base_model,
+        _ensure_venv_t5_exists,
+        _VENV_T5_DIR,
+    )
 
     resolved = _resolve_base_model(model_name)
     if needs_transformers_5(resolved):
-        venv_t5 = os.path.join(
-            os.path.expanduser("~"), ".unsloth", "studio", ".venv_t5"
-        )
-        if os.path.isdir(venv_t5):
-            sys.path.insert(0, venv_t5)
-            logger.info("Activated transformers 5.x from %s", venv_t5)
-        else:
-            # Fallback: pip install at runtime (slower, ~10-15s)
-            logger.warning(".venv_t5 not found at %s — installing at runtime", venv_t5)
-            import subprocess as sp
-
-            os.makedirs(venv_t5, exist_ok = True)
-            r1 = sp.run(
-                [
-                    sys.executable,
-                    "-m",
-                    "pip",
-                    "install",
-                    "--target",
-                    venv_t5,
-                    "--no-deps",
-                    "transformers==5.3.0",
-                ],
-                stdout = sp.PIPE,
-                stderr = sp.STDOUT,
+        if not _ensure_venv_t5_exists():
+            raise RuntimeError(
+                f"Cannot activate transformers 5.x: .venv_t5 missing at {_VENV_T5_DIR}"
             )
-            r2 = sp.run(
-                [
-                    sys.executable,
-                    "-m",
-                    "pip",
-                    "install",
-                    "--target",
-                    venv_t5,
-                    "--no-deps",
-                    "huggingface_hub==1.3.0",
-                ],
-                stdout = sp.PIPE,
-                stderr = sp.STDOUT,
-            )
-            if r1.returncode != 0 or r2.returncode != 0:
-                raise RuntimeError(
-                    f"Failed to install transformers 5.x into {venv_t5}. "
-                    f"pip returncode: transformers={r1.returncode}, huggingface_hub={r2.returncode}"
-                )
-            sys.path.insert(0, venv_t5)
+        if _VENV_T5_DIR not in sys.path:
+            sys.path.insert(0, _VENV_T5_DIR)
+        logger.info("Activated transformers 5.x from %s", _VENV_T5_DIR)
         # Propagate to child subprocesses (e.g. GGUF converter)
         _pp = os.environ.get("PYTHONPATH", "")
-        os.environ["PYTHONPATH"] = venv_t5 + (os.pathsep + _pp if _pp else "")
+        os.environ["PYTHONPATH"] = _VENV_T5_DIR + (os.pathsep + _pp if _pp else "")
     else:
         logger.info("Using default transformers (4.57.x) for %s", model_name)
 
diff --git a/studio/backend/core/inference/worker.py b/studio/backend/core/inference/worker.py
index 0693908178..2eb46f3217 100644
--- a/studio/backend/core/inference/worker.py
+++ b/studio/backend/core/inference/worker.py
@@ -42,59 +42,25 @@ def _activate_transformers_version(model_name: str) -> None:
     if backend_path not in sys.path:
         sys.path.insert(0, backend_path)
 
-    from utils.transformers_version import needs_transformers_5, _resolve_base_model
+    from utils.transformers_version import (
+        needs_transformers_5,
+        _resolve_base_model,
+        _ensure_venv_t5_exists,
+        _VENV_T5_DIR,
+    )
 
     resolved = _resolve_base_model(model_name)
     if needs_transformers_5(resolved):
-        venv_t5 = os.path.join(
-            os.path.expanduser("~"), ".unsloth", "studio", ".venv_t5"
-        )
-        if os.path.isdir(venv_t5):
-            sys.path.insert(0, venv_t5)
-            logger.info("Activated transformers 5.x from %s", venv_t5)
-        else:
-            # Fallback: pip install at runtime (slower, ~10-15s)
-            logger.warning(".venv_t5 not found at %s — installing at runtime", venv_t5)
-            import subprocess as sp
-
-            os.makedirs(venv_t5, exist_ok = True)
-            r1 = sp.run(
-                [
-                    sys.executable,
-                    "-m",
-                    "pip",
-                    "install",
-                    "--target",
-                    venv_t5,
-                    "--no-deps",
-                    "transformers==5.3.0",
-                ],
-                stdout = sp.PIPE,
-                stderr = sp.STDOUT,
+        if not _ensure_venv_t5_exists():
+            raise RuntimeError(
+                f"Cannot activate transformers 5.x: .venv_t5 missing at {_VENV_T5_DIR}"
             )
-            r2 = sp.run(
-                [
-                    sys.executable,
-                    "-m",
-                    "pip",
-                    "install",
-                    "--target",
-                    venv_t5,
-                    "--no-deps",
-                    "huggingface_hub==1.3.0",
-                ],
-                stdout = sp.PIPE,
-                stderr = sp.STDOUT,
-            )
-            if r1.returncode != 0 or r2.returncode != 0:
-                raise RuntimeError(
-                    f"Failed to install transformers 5.x into {venv_t5}. "
-                    f"pip returncode: transformers={r1.returncode}, huggingface_hub={r2.returncode}"
-                )
-            sys.path.insert(0, venv_t5)
+        if _VENV_T5_DIR not in sys.path:
+            sys.path.insert(0, _VENV_T5_DIR)
+        logger.info("Activated transformers 5.x from %s", _VENV_T5_DIR)
         # Propagate to child subprocesses (e.g. GGUF converter)
         _pp = os.environ.get("PYTHONPATH", "")
-        os.environ["PYTHONPATH"] = venv_t5 + (os.pathsep + _pp if _pp else "")
+        os.environ["PYTHONPATH"] = _VENV_T5_DIR + (os.pathsep + _pp if _pp else "")
     else:
         logger.info("Using default transformers (4.57.x) for %s", model_name)
 
diff --git a/studio/backend/core/training/worker.py b/studio/backend/core/training/worker.py
index 284fcf228d..ccd805b7ac 100644
--- a/studio/backend/core/training/worker.py
+++ b/studio/backend/core/training/worker.py
@@ -36,59 +36,25 @@ def _activate_transformers_version(model_name: str) -> None:
     if backend_path not in sys.path:
         sys.path.insert(0, backend_path)
 
-    from utils.transformers_version import needs_transformers_5, _resolve_base_model
+    from utils.transformers_version import (
+        needs_transformers_5,
+        _resolve_base_model,
+        _ensure_venv_t5_exists,
+        _VENV_T5_DIR,
+    )
 
     resolved = _resolve_base_model(model_name)
     if needs_transformers_5(resolved):
-        venv_t5 = os.path.join(
-            os.path.expanduser("~"), ".unsloth", "studio", ".venv_t5"
-        )
-        if os.path.isdir(venv_t5):
-            sys.path.insert(0, venv_t5)
-            logger.info("Activated transformers 5.x from %s", venv_t5)
-        else:
-            # Fallback: pip install at runtime (slower, ~10-15s)
-            logger.warning(".venv_t5 not found at %s — installing at runtime", venv_t5)
-            import subprocess as sp
-
-            os.makedirs(venv_t5, exist_ok = True)
-            r1 = sp.run(
-                [
-                    sys.executable,
-                    "-m",
-                    "pip",
-                    "install",
-                    "--target",
-                    venv_t5,
-                    "--no-deps",
-                    "transformers==5.3.0",
-                ],
-                stdout = sp.PIPE,
-                stderr = sp.STDOUT,
+        if not _ensure_venv_t5_exists():
+            raise RuntimeError(
+                f"Cannot activate transformers 5.x: .venv_t5 missing at {_VENV_T5_DIR}"
             )
-            r2 = sp.run(
-                [
-                    sys.executable,
-                    "-m",
-                    "pip",
-                    "install",
-                    "--target",
-                    venv_t5,
-                    "--no-deps",
-                    "huggingface_hub==1.3.0",
-                ],
-                stdout = sp.PIPE,
-                stderr = sp.STDOUT,
-            )
-            if r1.returncode != 0 or r2.returncode != 0:
-                raise RuntimeError(
-                    f"Failed to install transformers 5.x into {venv_t5}. "
-                    f"pip returncode: transformers={r1.returncode}, huggingface_hub={r2.returncode}"
-                )
-            sys.path.insert(0, venv_t5)
+        if _VENV_T5_DIR not in sys.path:
+            sys.path.insert(0, _VENV_T5_DIR)
+        logger.info("Activated transformers 5.x from %s", _VENV_T5_DIR)
         # Propagate to child subprocesses (e.g. GGUF converter)
         _pp = os.environ.get("PYTHONPATH", "")
-        os.environ["PYTHONPATH"] = venv_t5 + (os.pathsep + _pp if _pp else "")
+        os.environ["PYTHONPATH"] = _VENV_T5_DIR + (os.pathsep + _pp if _pp else "")
     else:
         logger.info("Using default transformers (4.57.x) for %s", model_name)
 
diff --git a/studio/backend/requirements/extras-no-deps.txt b/studio/backend/requirements/extras-no-deps.txt
index 3bdce81cc1..4b5aa86b5f 100644
--- a/studio/backend/requirements/extras-no-deps.txt
+++ b/studio/backend/requirements/extras-no-deps.txt
@@ -11,4 +11,4 @@ git+https://github.com/meta-pytorch/OpenEnv.git
 # executorch>=1.0.1               # 41.5 MB - no imports in unsloth/zoo/studio
 torch-c-dlpack-ext
 sentence_transformers==5.2.0
-transformers==4.57.1
+transformers==4.57.6
diff --git a/studio/backend/requirements/single-env/constraints.txt b/studio/backend/requirements/single-env/constraints.txt
index 1789bbf713..156f78567e 100644
--- a/studio/backend/requirements/single-env/constraints.txt
+++ b/studio/backend/requirements/single-env/constraints.txt
@@ -1,6 +1,6 @@
 # Single-env pins for unsloth + studio + data-designer
 # Keep compatible with unsloth transformers bounds.
-transformers==4.57.1
+transformers==4.57.6
 trl==0.23.1
 huggingface-hub==0.36.2
 
diff --git a/studio/backend/utils/transformers_version.py b/studio/backend/utils/transformers_version.py
index 5666b3be35..60b43500c0 100644
--- a/studio/backend/utils/transformers_version.py
+++ b/studio/backend/utils/transformers_version.py
@@ -26,6 +26,7 @@ import json
 import structlog
 from loggers import get_logger
 import os
+import shutil
 import subprocess
 import sys
 from pathlib import Path
@@ -58,7 +59,7 @@ _tokenizer_class_cache: dict[str, bool] = {}
 
 # Versions
 TRANSFORMERS_5_VERSION = "5.3.0"
-TRANSFORMERS_DEFAULT_VERSION = "4.57.1"
+TRANSFORMERS_DEFAULT_VERSION = "4.57.6"
 
 # Pre-installed directory for transformers 5.x — created by setup.sh / setup.ps1
 _VENV_T5_DIR = str(Path.home() / ".unsloth" / "studio" / ".venv_t5")
@@ -216,15 +217,87 @@ def _purge_modules() -> int:
     return len(to_remove)
 
 
-def _ensure_venv_t5_exists() -> bool:
-    """Ensure .venv_t5/ exists. Install at runtime if missing."""
-    if os.path.isdir(_VENV_T5_DIR) and os.listdir(_VENV_T5_DIR):
-        return True
+_VENV_T5_PACKAGES = (
+    f"transformers=={TRANSFORMERS_5_VERSION}",
+    "huggingface_hub==1.7.1",
+    "hf_xet==1.4.2",
+    "tiktoken",
+)
 
-    logger.warning(".venv_t5 not found at %s — installing at runtime", _VENV_T5_DIR)
-    os.makedirs(_VENV_T5_DIR, exist_ok = True)
-    for pkg in (f"transformers=={TRANSFORMERS_5_VERSION}", "huggingface_hub==1.3.0"):
-        cmd = [
+
+def _venv_t5_is_valid() -> bool:
+    """Return True if .venv_t5/ has all required packages at the correct versions."""
+    if not os.path.isdir(_VENV_T5_DIR) or not os.listdir(_VENV_T5_DIR):
+        return False
+    # Check that the key package directories exist AND match the required version
+    for pkg_spec in _VENV_T5_PACKAGES:
+        parts = pkg_spec.split("==")
+        pkg_name = parts[0]
+        pkg_version = parts[1] if len(parts) > 1 else None
+        pkg_name_norm = pkg_name.replace("-", "_")
+        # Check directory exists
+        if not any(
+            (Path(_VENV_T5_DIR) / d).is_dir()
+            for d in (pkg_name_norm, pkg_name_norm.replace("_", "-"))
+        ):
+            return False
+        # For unpinned packages, existence is enough
+        if pkg_version is None:
+            continue
+        # Check version via .dist-info metadata
+        dist_info_found = False
+        for di in Path(_VENV_T5_DIR).glob(f"{pkg_name_norm}-*.dist-info"):
+            metadata = di / "METADATA"
+            if not metadata.is_file():
+                continue
+            for line in metadata.read_text(errors = "replace").splitlines():
+                if line.startswith("Version:"):
+                    installed_ver = line.split(":", 1)[1].strip()
+                    if installed_ver != pkg_version:
+                        logger.info(
+                            ".venv_t5 has %s==%s but need %s",
+                            pkg_name,
+                            installed_ver,
+                            pkg_version,
+                        )
+                        return False
+                    dist_info_found = True
+                    break
+            if dist_info_found:
+                break
+        if not dist_info_found:
+            return False
+    return True
+
+
+def _install_to_venv_t5(pkg: str) -> bool:
+    """Install a single package into .venv_t5/, preferring uv then pip."""
+    # Try uv first (faster) if already on PATH -- do NOT install uv at runtime
+    if shutil.which("uv"):
+        result = subprocess.run(
+            [
+                "uv",
+                "pip",
+                "install",
+                "--python",
+                sys.executable,
+                "--target",
+                _VENV_T5_DIR,
+                "--no-deps",
+                "--upgrade",
+                pkg,
+            ],
+            stdout = subprocess.PIPE,
+            stderr = subprocess.STDOUT,
+            text = True,
+        )
+        if result.returncode == 0:
+            return True
+        logger.warning("uv install of %s failed, falling back to pip", pkg)
+
+    # Fallback to pip
+    result = subprocess.run(
+        [
             sys.executable,
             "-m",
             "pip",
@@ -232,13 +305,31 @@ def _ensure_venv_t5_exists() -> bool:
             "--target",
             _VENV_T5_DIR,
             "--no-deps",
+            "--upgrade",
             pkg,
-        ]
-        result = subprocess.run(
-            cmd, stdout = subprocess.PIPE, stderr = subprocess.STDOUT, text = True
-        )
-        if result.returncode != 0:
-            logger.error("pip install failed:\n%s", result.stdout)
+        ],
+        stdout = subprocess.PIPE,
+        stderr = subprocess.STDOUT,
+        text = True,
+    )
+    if result.returncode != 0:
+        logger.error("install failed:\n%s", result.stdout)
+        return False
+    return True
+
+
+def _ensure_venv_t5_exists() -> bool:
+    """Ensure .venv_t5/ exists with all required packages. Install if missing."""
+    if _venv_t5_is_valid():
+        return True
+
+    logger.warning(
+        ".venv_t5 not found or incomplete at %s -- installing at runtime", _VENV_T5_DIR
+    )
+    shutil.rmtree(_VENV_T5_DIR, ignore_errors = True)
+    os.makedirs(_VENV_T5_DIR, exist_ok = True)
+    for pkg in _VENV_T5_PACKAGES:
+        if not _install_to_venv_t5(pkg):
             return False
     logger.info("Installed transformers 5.x to %s", _VENV_T5_DIR)
     return True
diff --git a/studio/install_python_stack.py b/studio/install_python_stack.py
index 20011a298a..a141c64425 100644
--- a/studio/install_python_stack.py
+++ b/studio/install_python_stack.py
@@ -140,15 +140,15 @@ def _bootstrap_uv() -> bool:
     global UV_NEEDS_SYSTEM
     if not shutil.which("uv"):
         return False
-    # Probe: try a dry-run install without --system.
-    # If uv can't find a venv it exits with code 2.
+    # Probe: try a dry-run install targeting the current Python explicitly.
+    # Without --python, uv can ignore the activated venv on some platforms.
     probe = subprocess.run(
-        ["uv", "pip", "install", "--dry-run", "pip"],
+        ["uv", "pip", "install", "--dry-run", "--python", sys.executable, "pip"],
         stdout = subprocess.PIPE,
         stderr = subprocess.STDOUT,
     )
     if probe.returncode != 0:
-        # Retry with --system to confirm it works
+        # Retry with --system (some envs need it when uv can't find a venv)
         probe_sys = subprocess.run(
             ["uv", "pip", "install", "--dry-run", "--system", "pip"],
             stdout = subprocess.PIPE,
@@ -204,6 +204,10 @@ def _build_uv_cmd(args: tuple[str, ...]) -> list[str]:
     cmd = ["uv", "pip", "install"]
     if UV_NEEDS_SYSTEM:
         cmd.append("--system")
+    # Always pass --python so uv targets the correct environment.
+    # Without this, uv can ignore an activated venv and install into
+    # the system Python (observed on Colab and similar environments).
+    cmd.extend(["--python", sys.executable])
     cmd.extend(_translate_pip_args_for_uv(args))
     cmd.append("--torch-backend=auto")
     return cmd
diff --git a/studio/setup.ps1 b/studio/setup.ps1
index 2420448deb..3930ad686e 100644
--- a/studio/setup.ps1
+++ b/studio/setup.ps1
@@ -8,7 +8,7 @@
     Always installs Node.js if needed. When running from pip install:
     skips frontend build (already bundled). When running from git repo:
     full setup including frontend build.
-    Requires an NVIDIA GPU -- CPU-only machines are not supported.
+    Supports NVIDIA GPU (full training + inference) and CPU-only (GGUF chat mode).
 .NOTES
     Usage: powershell -ExecutionPolicy Bypass -File setup.ps1
 #>
@@ -107,11 +107,15 @@ function Find-Nvcc {
 # Returns e.g. "80" for A100 (8.0), "89" for RTX 4090 (8.9), etc.
 # Returns $null if detection fails.
 function Get-CudaComputeCapability {
-    $nvSmi = Get-Command nvidia-smi -ErrorAction SilentlyContinue
-    if (-not $nvSmi) { return $null }
+    # Use the resolved absolute path ($NvidiaSmiExe) to survive Refresh-Environment
+    $smiExe = if ($script:NvidiaSmiExe) { $script:NvidiaSmiExe } else {
+        $cmd = Get-Command nvidia-smi -ErrorAction SilentlyContinue
+        if ($cmd) { $cmd.Source } else { $null }
+    }
+    if (-not $smiExe) { return $null }
 
     try {
-        $raw = & nvidia-smi --query-gpu=compute_cap --format=csv,noheader 2>$null
+        $raw = & $smiExe --query-gpu=compute_cap --format=csv,noheader 2>$null
         if ($LASTEXITCODE -ne 0 -or -not $raw) { return $null }
 
         # nvidia-smi may return multiple GPUs; take the first one
@@ -168,14 +172,17 @@ function Get-NvccMaxArch {
 # https://download.pytorch.org/whl/<tag>. The tag must not exceed the driver's
 # capability: e.g. driver "CUDA Version: 12.9" → cu128 (not cu130).
 function Get-PytorchCudaTag {
-    $nvSmi = Get-Command nvidia-smi -ErrorAction SilentlyContinue
-    if (-not $nvSmi) { return "cu124" }
+    $smiExe = if ($script:NvidiaSmiExe) { $script:NvidiaSmiExe } else {
+        $cmd = Get-Command nvidia-smi -ErrorAction SilentlyContinue
+        if ($cmd) { $cmd.Source } else { $null }
+    }
+    if (-not $smiExe) { return "cu124" }
 
     try {
         # 2>&1 | Out-String merges stderr into stdout then converts to a single
-        # string.  Plain 2>$null doesn't fully suppress stderr in PS 5.1 —
+        # string.  Plain 2>$null doesn't fully suppress stderr in PS 5.1 --
         # ErrorRecord objects leak into $output and break the -match.
-        $output = & nvidia-smi 2>&1 | Out-String
+        $output = & $smiExe 2>&1 | Out-String
         if ($output -match 'CUDA Version:\s+(\d+)\.(\d+)') {
             $major = [int]$Matches[1]
             $minor = [int]$Matches[2]
@@ -251,23 +258,50 @@ Write-Host "+==============================================+" -ForegroundColor G
 # ==========================================================================
 
 # ============================================
-# 1a. GPU requirement check
+# 1a. GPU detection
 # ============================================
 $HasNvidiaSmi = $false
+$NvidiaSmiExe = $null  # Absolute path -- survives Refresh-Environment
 try {
-    nvidia-smi 2>&1 | Out-Null
-    if ($LASTEXITCODE -eq 0) { $HasNvidiaSmi = $true }
+    $nvSmiCmd = Get-Command nvidia-smi -ErrorAction SilentlyContinue
+    if ($nvSmiCmd) {
+        & $nvSmiCmd.Source 2>&1 | Out-Null
+        if ($LASTEXITCODE -eq 0) {
+            $HasNvidiaSmi = $true
+            $NvidiaSmiExe = $nvSmiCmd.Source
+        }
+    }
 } catch {}
+# Fallback: nvidia-smi may not be on PATH even though a GPU + driver exist.
+# Check the default install location and the Windows driver store.
+if (-not $HasNvidiaSmi) {
+    $nvSmiDefaults = @(
+        "$env:ProgramFiles\NVIDIA Corporation\NVSMI\nvidia-smi.exe",
+        "$env:SystemRoot\System32\nvidia-smi.exe"
+    )
+    foreach ($p in $nvSmiDefaults) {
+        if (Test-Path $p) {
+            try {
+                & $p 2>&1 | Out-Null
+                if ($LASTEXITCODE -eq 0) {
+                    $HasNvidiaSmi = $true
+                    $NvidiaSmiExe = $p
+                    Write-Host "   Found nvidia-smi at $(Split-Path $p -Parent)" -ForegroundColor Gray
+                    break
+                }
+            } catch {}
+        }
+    }
+}
 if (-not $HasNvidiaSmi) {
     Write-Host ""
-    Write-Host "[ERROR] Unsloth Studio requires an NVIDIA GPU." -ForegroundColor Red
-    Write-Host "        CPU-only machines are not supported." -ForegroundColor Red
+    Write-Host "[WARN] No NVIDIA GPU detected. Studio will run in chat-only (GGUF) mode." -ForegroundColor Yellow
+    Write-Host "       Training and GPU inference require an NVIDIA GPU with drivers installed." -ForegroundColor Yellow
+    Write-Host "       https://www.nvidia.com/Download/index.aspx" -ForegroundColor Yellow
     Write-Host ""
-    Write-Host "        If you have an NVIDIA GPU, ensure the driver is installed:" -ForegroundColor Yellow
-    Write-Host "        https://www.nvidia.com/Download/index.aspx" -ForegroundColor Yellow
-    exit 1
+} else {
+    Write-Host "[OK] NVIDIA GPU detected" -ForegroundColor Green
 }
-Write-Host "[OK] NVIDIA GPU detected" -ForegroundColor Green
 
 # ============================================
 # 1a.5. Windows Long Paths (required for deep node_modules / Python paths)
@@ -341,6 +375,30 @@ if (-not $HasCmake) {
             $HasCmake = $null -ne (Get-Command cmake -ErrorAction SilentlyContinue)
         } catch { }
     }
+    # winget may succeed but cmake isn't on PATH yet (MSI PATH changes need a
+    # new shell). Try the default install location as a fallback.
+    if (-not $HasCmake) {
+        $cmakeDefaults = @(
+            "$env:ProgramFiles\CMake\bin",
+            "${env:ProgramFiles(x86)}\CMake\bin",
+            "$env:LOCALAPPDATA\CMake\bin"
+        )
+        foreach ($d in $cmakeDefaults) {
+            if (Test-Path (Join-Path $d "cmake.exe")) {
+                $env:Path = "$d;$env:Path"
+                # Persist to user PATH so Refresh-Environment does not drop it later
+                $userPath = [Environment]::GetEnvironmentVariable('Path', 'User')
+                if (-not $userPath -or $userPath -notlike "*$d*") {
+                    [Environment]::SetEnvironmentVariable('Path', "$d;$userPath", 'User')
+                }
+                $HasCmake = $null -ne (Get-Command cmake -ErrorAction SilentlyContinue)
+                if ($HasCmake) {
+                    Write-Host "   Found cmake at $d (added to PATH)" -ForegroundColor Gray
+                    break
+                }
+            }
+        }
+    }
     if ($HasCmake) {
         Write-Host "[OK] CMake installed" -ForegroundColor Green
     } else {
@@ -389,6 +447,7 @@ if ($vsResult) {
 # ============================================
 # 1e. CUDA Toolkit (nvcc for llama.cpp build + env vars)
 # ============================================
+if ($HasNvidiaSmi) {
 # IMPORTANT: The CUDA Toolkit version must be <= the max CUDA version the
 # NVIDIA driver supports.  nvidia-smi reports this as "CUDA Version: X.Y".
 # If we install a toolkit newer than the driver supports, llama-server will
@@ -397,7 +456,7 @@ if ($vsResult) {
 # -- Detect max CUDA version the driver supports --
 $DriverMaxCuda = $null
 try {
-    $smiOut = nvidia-smi 2>&1 | Out-String
+    $smiOut = & $NvidiaSmiExe 2>&1 | Out-String
     if ($smiOut -match "CUDA Version:\s+([\d]+)\.([\d]+)") {
         $DriverMaxCuda = "$($Matches[1]).$($Matches[2])"
         Write-Host "   Driver supports up to CUDA $DriverMaxCuda" -ForegroundColor Gray
@@ -624,11 +683,24 @@ if ($VsInstallPath -and $CudaToolkitRoot) {
                 Copy-Item "$cudaExtras\*" $vsCustomizations -Force -ErrorAction Stop
                 Write-Host "   [OK] CUDA VS integration files installed" -ForegroundColor Green
             } catch {
-                Write-Host "   [WARN] Could not copy CUDA VS integration files (may need admin)" -ForegroundColor Yellow
-                Write-Host "          Manual fix: copy contents of" -ForegroundColor Yellow
-                Write-Host "            $cudaExtras" -ForegroundColor Cyan
-                Write-Host "          into:" -ForegroundColor Yellow
-                Write-Host "            $vsCustomizations" -ForegroundColor Cyan
+                # Direct copy failed (needs admin). Try elevated copy via Start-Process.
+                try {
+                    $copyCmd = "Copy-Item '$cudaExtras\*' '$vsCustomizations' -Force"
+                    Start-Process powershell -ArgumentList "-NoProfile -Command $copyCmd" -Verb RunAs -Wait -ErrorAction Stop
+                    $hasTargetsRetry = Get-ChildItem $vsCustomizations -Filter "CUDA *.targets" -ErrorAction SilentlyContinue
+                    if ($hasTargetsRetry) {
+                        Write-Host "   [OK] CUDA VS integration files installed (elevated)" -ForegroundColor Green
+                    } else {
+                        throw "Copy did not produce .targets files"
+                    }
+                } catch {
+                    Write-Host "   [WARN] Could not copy CUDA VS integration files" -ForegroundColor Yellow
+                    Write-Host "          The llama.cpp build may fail with 'No CUDA toolset found'." -ForegroundColor Yellow
+                    Write-Host "          Manual fix: copy contents of" -ForegroundColor Yellow
+                    Write-Host "            $cudaExtras" -ForegroundColor Cyan
+                    Write-Host "          into:" -ForegroundColor Yellow
+                    Write-Host "            $vsCustomizations" -ForegroundColor Cyan
+                }
             }
         }
     }
@@ -643,6 +715,9 @@ Write-Host "   CudaToolkitDir = $CudaToolkitRoot\" -ForegroundColor Gray
 if (-not $CudaArch) {
     Write-Host "   [WARN] Could not detect compute capability -- cmake will use defaults" -ForegroundColor Yellow
 }
+} else {
+    Write-Host "[SKIP] CUDA Toolkit -- no NVIDIA GPU detected" -ForegroundColor Yellow
+}
 
 # ============================================
 # 1f. Node.js / npm (skip if pip-installed -- only needed for frontend build)
@@ -748,9 +823,39 @@ Write-Host ""
 # ==========================================================================
 #  PHASE 2: Frontend build (skip if pip-installed -- already bundled)
 # ==========================================================================
+$DistDir = Join-Path $FrontendDir "dist"
+# Skip build if dist/ exists and no tracked input is newer than dist/.
+# Checks src/, public/, package.json, config files -- not just src/.
+$NeedFrontendBuild = $true
 if ($IsPipInstall) {
+    $NeedFrontendBuild = $false
     Write-Host "[OK] Running from pip install - frontend already bundled, skipping build" -ForegroundColor Green
-} else {
+} elseif (Test-Path $DistDir) {
+    $DistTime = (Get-Item $DistDir).LastWriteTime
+    $NewerFile = $null
+    # Check src/ and public/ recursively (probe paths directly, not via -Include)
+    foreach ($subDir in @("src", "public")) {
+        $subPath = Join-Path $FrontendDir $subDir
+        if (Test-Path $subPath) {
+            $NewerFile = Get-ChildItem -Path $subPath -Recurse -File -ErrorAction SilentlyContinue |
+                Where-Object { $_.LastWriteTime -gt $DistTime } | Select-Object -First 1
+            if ($NewerFile) { break }
+        }
+    }
+    # Also check all top-level files (package.json, bun.lock, vite.config.ts, index.html, etc.)
+    if (-not $NewerFile) {
+        $NewerFile = Get-ChildItem -Path $FrontendDir -File -ErrorAction SilentlyContinue |
+            Where-Object { $_.LastWriteTime -gt $DistTime } |
+            Select-Object -First 1
+    }
+    if (-not $NewerFile) {
+        $NeedFrontendBuild = $false
+        Write-Host "[OK] Frontend already built and up to date -- skipping build" -ForegroundColor Green
+    } else {
+        Write-Host "[INFO] Frontend source changed since last build -- rebuilding..." -ForegroundColor Yellow
+    }
+}
+if ($NeedFrontendBuild -and -not $IsPipInstall) {
     Write-Host ""
     Write-Host "Building frontend..." -ForegroundColor Cyan
     # npm writes warnings to stderr; lower ErrorActionPreference so PS doesn't
@@ -758,9 +863,6 @@ if ($IsPipInstall) {
     $prevEAP_npm = $ErrorActionPreference
     $ErrorActionPreference = "Continue"
     Push-Location $FrontendDir
-    # Remove stale node_modules and package-lock.json to avoid version conflicts
-    if (Test-Path "node_modules") { Remove-Item -Recurse -Force "node_modules" }
-    if (Test-Path "package-lock.json") { Remove-Item -Force "package-lock.json" }
     npm install 2>&1 | Out-Null
     if ($LASTEXITCODE -ne 0) {
         Pop-Location
@@ -845,7 +947,35 @@ $ErrorActionPreference = "Continue"
 
 $ActivateScript = Join-Path $VenvDir "Scripts\Activate.ps1"
 . $ActivateScript
-pip install --upgrade pip 2>&1 | Out-Null
+
+# Try to use uv (much faster than pip), fall back to pip if unavailable
+$UseUv = $false
+if (Get-Command uv -ErrorAction SilentlyContinue) {
+    $UseUv = $true
+} else {
+    Write-Host "   Installing uv package manager..." -ForegroundColor Cyan
+    try {
+        powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" 2>&1 | Out-Null
+        Refresh-Environment
+        # Re-activate venv since Refresh-Environment rebuilds PATH from
+        # registry and drops the venv's Scripts directory
+        . $ActivateScript
+        if (Get-Command uv -ErrorAction SilentlyContinue) { $UseUv = $true }
+    } catch { }
+}
+
+# Helper: install a package, preferring uv with pip fallback
+function Fast-Install {
+    param([Parameter(ValueFromRemainingArguments=$true)]$Args_)
+    if ($UseUv) {
+        $VenvPy = (Get-Command python).Source
+        $result = & uv pip install --python $VenvPy @Args_ 2>&1
+        if ($LASTEXITCODE -eq 0) { return }
+    }
+    & python -m pip install @Args_ 2>&1
+}
+
+Fast-Install --upgrade pip | Out-Null
 
 # if (-not $IsPipInstall) {
 #     # Running from repo: copy requirements and do editable install
@@ -880,16 +1010,37 @@ $env:TORCHINDUCTOR_CACHE_DIR = $TorchCacheDir
 [Environment]::SetEnvironmentVariable('TORCHINDUCTOR_CACHE_DIR', $TorchCacheDir, 'User')
 Write-Host "[OK] TORCHINDUCTOR_CACHE_DIR set to $TorchCacheDir (avoids MAX_PATH issues)" -ForegroundColor Green
 
-$CuTag = Get-PytorchCudaTag
-Write-Host "   Installing PyTorch with CUDA support ($CuTag)..." -ForegroundColor Cyan
-pip install torch torchvision torchaudio --index-url "https://download.pytorch.org/whl/$CuTag" 2>&1 | Out-Null
+if ($HasNvidiaSmi) {
+    $CuTag = Get-PytorchCudaTag
+    Write-Host "   Installing PyTorch with CUDA support ($CuTag)..." -ForegroundColor Cyan
+    Write-Host "   (This download is ~2.8 GB -- may take a few minutes)" -ForegroundColor Gray
+    $output = Fast-Install torch torchvision torchaudio --index-url "https://download.pytorch.org/whl/$CuTag" | Out-String
+    if ($LASTEXITCODE -ne 0) {
+        Write-Host "[FAILED] PyTorch CUDA install failed (exit code $LASTEXITCODE)" -ForegroundColor Red
+        Write-Host $output -ForegroundColor Red
+        exit 1
+    }
 
-# Install Triton for Windows (enables torch.compile — without it training can hang)
-Write-Host "   Installing Triton for Windows..." -ForegroundColor Cyan
-pip install "triton-windows<3.7" 2>&1 | Out-Null
-Write-Host "[OK] Triton for Windows installed (enables torch.compile)" -ForegroundColor Green
+    # Install Triton for Windows (enables torch.compile -- without it training can hang)
+    Write-Host "   Installing Triton for Windows..." -ForegroundColor Cyan
+    $output = Fast-Install "triton-windows<3.7" | Out-String
+    if ($LASTEXITCODE -ne 0) {
+        Write-Host "[WARN] Triton install failed -- torch.compile may not work" -ForegroundColor Yellow
+        Write-Host $output -ForegroundColor Yellow
+    } else {
+        Write-Host "[OK] Triton for Windows installed (enables torch.compile)" -ForegroundColor Green
+    }
+} else {
+    Write-Host "   Installing PyTorch (CPU-only)..." -ForegroundColor Cyan
+    $output = Fast-Install torch torchvision torchaudio --index-url "https://download.pytorch.org/whl/cpu" | Out-String
+    if ($LASTEXITCODE -ne 0) {
+        Write-Host "[FAILED] PyTorch install failed (exit code $LASTEXITCODE)" -ForegroundColor Red
+        Write-Host $output -ForegroundColor Red
+        exit 1
+    }
+}
 
-# Ordered heavy dependency installation — shared cross-platform script
+# Ordered heavy dependency installation -- shared cross-platform script
 Write-Host "   Running ordered dependency installation..." -ForegroundColor Cyan
 python "$PSScriptRoot\install_python_stack.py"
 # Restore ErrorActionPreference after pip/python work
@@ -898,7 +1049,7 @@ $ErrorActionPreference = $prevEAP
 # ── Pre-install transformers 5.x into .venv_t5/ ──
 # Models like GLM-4.7-Flash need transformers>=5.3.0. Instead of pip-installing
 # at runtime (slow, ~10-15s), we pre-install into a separate directory.
-# The training subprocess just prepends .venv_t5/ to sys.path — instant switch.
+# The training subprocess just prepends .venv_t5/ to sys.path -- instant switch.
 Write-Host ""
 Write-Host "   Pre-installing transformers 5.x for newer model support..." -ForegroundColor Cyan
 $VenvT5Dir = Join-Path $env:USERPROFILE ".unsloth\studio\.venv_t5"
@@ -906,17 +1057,20 @@ if (Test-Path $VenvT5Dir) { Remove-Item -Recurse -Force $VenvT5Dir }
 New-Item -ItemType Directory -Path $VenvT5Dir -Force | Out-Null
 $prevEAP_t5 = $ErrorActionPreference
 $ErrorActionPreference = "Continue"
-pip install --target $VenvT5Dir --no-deps "transformers==5.3.0" 2>&1 | Out-Null
-if ($LASTEXITCODE -ne 0) {
-    Write-Host "[FAIL] Could not install transformers 5.3.0 into .venv_t5/" -ForegroundColor Red
-    $ErrorActionPreference = $prevEAP_t5
-    exit 1
+foreach ($pkg in @("transformers==5.3.0", "huggingface_hub==1.7.1", "hf_xet==1.4.2")) {
+    $output = Fast-Install --target $VenvT5Dir --no-deps $pkg | Out-String
+    if ($LASTEXITCODE -ne 0) {
+        Write-Host "[FAIL] Could not install $pkg into .venv_t5/" -ForegroundColor Red
+        Write-Host $output -ForegroundColor Red
+        $ErrorActionPreference = $prevEAP_t5
+        exit 1
+    }
 }
-pip install --target $VenvT5Dir --no-deps "huggingface_hub==1.3.0" 2>&1 | Out-Null
+# tiktoken is needed by Qwen-family tokenizers -- install with deps since
+# regex/requests may be missing on Windows
+$output = Fast-Install --target $VenvT5Dir tiktoken | Out-String
 if ($LASTEXITCODE -ne 0) {
-    Write-Host "[FAIL] Could not install huggingface_hub 1.3.0 into .venv_t5/" -ForegroundColor Red
-    $ErrorActionPreference = $prevEAP_t5
-    exit 1
+    Write-Host "[WARN] Could not install tiktoken into .venv_t5/ -- Qwen tokenizers may fail" -ForegroundColor Yellow
 }
 $ErrorActionPreference = $prevEAP_t5
 Write-Host "[OK] Transformers 5.x pre-installed to .venv_t5/" -ForegroundColor Green
@@ -982,12 +1136,46 @@ $LlamaCppDir = Join-Path $UnslothHome "llama.cpp"
 $BuildDir = Join-Path $LlamaCppDir "build"
 $LlamaServerBin = Join-Path $BuildDir "bin\Release\llama-server.exe"
 
+$HasCmakeForBuild = $null -ne (Get-Command cmake -ErrorAction SilentlyContinue)
+
+# Check if existing llama-server matches current GPU mode. A CUDA-built binary
+# on a now-CPU-only machine (or vice versa) needs to be rebuilt.
+$NeedRebuild = $false
 if (Test-Path $LlamaServerBin) {
+    $CmakeCacheFile = Join-Path $BuildDir "CMakeCache.txt"
+    if (Test-Path $CmakeCacheFile) {
+        $cachedCuda = Select-String -Path $CmakeCacheFile -Pattern 'GGML_CUDA:BOOL=ON' -Quiet
+        if ($HasNvidiaSmi -and -not $cachedCuda) {
+            Write-Host "   Existing llama-server is CPU-only but GPU is available -- rebuilding" -ForegroundColor Yellow
+            $NeedRebuild = $true
+        } elseif (-not $HasNvidiaSmi -and $cachedCuda) {
+            Write-Host "   Existing llama-server was built with CUDA but no GPU detected -- rebuilding" -ForegroundColor Yellow
+            $NeedRebuild = $true
+        }
+    }
+}
+
+if ((Test-Path $LlamaServerBin) -and -not $NeedRebuild) {
     Write-Host ""
     Write-Host "[OK] llama-server already exists at $LlamaServerBin" -ForegroundColor Green
+} elseif (-not $HasCmakeForBuild) {
+    Write-Host ""
+    if (-not $HasNvidiaSmi) {
+        # CPU-only machines depend entirely on llama-server for GGUF chat -- cmake is required
+        Write-Host "[ERROR] CMake is required to build llama-server for GGUF chat mode." -ForegroundColor Red
+        Write-Host "        Install CMake from https://cmake.org/download/ and re-run setup." -ForegroundColor Yellow
+        exit 1
+    }
+    Write-Host "[SKIP] llama-server build -- cmake not available" -ForegroundColor Yellow
+    Write-Host "       GGUF inference and export will not be available." -ForegroundColor Yellow
+    Write-Host "       Install CMake from https://cmake.org/download/ and re-run setup." -ForegroundColor Yellow
 } else {
     Write-Host ""
-    Write-Host "Building llama.cpp with CUDA support..." -ForegroundColor Cyan
+    if ($HasNvidiaSmi) {
+        Write-Host "Building llama.cpp with CUDA support..." -ForegroundColor Cyan
+    } else {
+        Write-Host "Building llama.cpp (CPU-only, no NVIDIA GPU detected)..." -ForegroundColor Cyan
+    }
     Write-Host "   This typically takes 5-10 minutes on first build." -ForegroundColor Gray
     Write-Host ""
 
@@ -1007,17 +1195,19 @@ if (Test-Path $LlamaServerBin) {
     # Re-sanitize CUDA_PATH_V* vars — Refresh-Environment (called during
     # Node/Python installs above) may have repopulated conflicting versioned
     # vars from the Machine registry.
-    $cudaPathVars2 = @([Environment]::GetEnvironmentVariables('Process').Keys | Where-Object { $_ -match '^CUDA_PATH_V' })
-    foreach ($v2 in $cudaPathVars2) {
-        [Environment]::SetEnvironmentVariable($v2, $null, 'Process')
+    if ($HasNvidiaSmi -and $CudaToolkitRoot) {
+        $cudaPathVars2 = @([Environment]::GetEnvironmentVariables('Process').Keys | Where-Object { $_ -match '^CUDA_PATH_V' })
+        foreach ($v2 in $cudaPathVars2) {
+            [Environment]::SetEnvironmentVariable($v2, $null, 'Process')
+        }
+        $tkDirName2 = Split-Path $CudaToolkitRoot -Leaf
+        if ($tkDirName2 -match '^v(\d+)\.(\d+)') {
+            [Environment]::SetEnvironmentVariable("CUDA_PATH_V$($Matches[1])_$($Matches[2])", $CudaToolkitRoot, 'Process')
+        }
+        # Also re-assert CUDA_PATH and CudaToolkitDir in case they were overwritten
+        [Environment]::SetEnvironmentVariable('CUDA_PATH', $CudaToolkitRoot, 'Process')
+        [Environment]::SetEnvironmentVariable('CudaToolkitDir', "$CudaToolkitRoot\", 'Process')
     }
-    $tkDirName2 = Split-Path $CudaToolkitRoot -Leaf
-    if ($tkDirName2 -match '^v(\d+)\.(\d+)') {
-        [Environment]::SetEnvironmentVariable("CUDA_PATH_V$($Matches[1])_$($Matches[2])", $CudaToolkitRoot, 'Process')
-    }
-    # Also re-assert CUDA_PATH and CudaToolkitDir in case they were overwritten
-    [Environment]::SetEnvironmentVariable('CUDA_PATH', $CudaToolkitRoot, 'Process')
-    [Environment]::SetEnvironmentVariable('CudaToolkitDir', "$CudaToolkitRoot\", 'Process')
 
     # -- Step A: Clone or pull llama.cpp --
 
@@ -1037,7 +1227,14 @@ if (Test-Path $LlamaServerBin) {
         }
     }
 
-    # -- Step B: cmake configure (CUDA + Unsloth flags) --
+    # -- Step B: cmake configure --
+    # Clean stale CMake cache to prevent previous CUDA settings from leaking
+    # into a CPU-only rebuild (or vice versa).
+    $CmakeCacheFile = Join-Path $BuildDir "CMakeCache.txt"
+    if (Test-Path $CmakeCacheFile) {
+        Remove-Item -Recurse -Force $BuildDir
+    }
+
     if ($BuildOk) {
         Write-Host ""
         Write-Host "--- cmake configure ---" -ForegroundColor Cyan
@@ -1066,37 +1263,45 @@ if (Test-Path $LlamaServerBin) {
             $CmakeArgs += '-DLLAMA_CURL=OFF'
         }
         $CmakeArgs += '-DCMAKE_EXE_LINKER_FLAGS=/NODEFAULTLIB:LIBCMT'
-        # CUDA flags (Unsloth-aligned)
-        $CmakeArgs += '-DGGML_CUDA=ON'
-        $CmakeArgs += "-DCUDAToolkit_ROOT=$CudaToolkitRoot"
-        $CmakeArgs += "-DCUDA_TOOLKIT_ROOT_DIR=$CudaToolkitRoot"
-        $CmakeArgs += "-DCMAKE_CUDA_COMPILER=$NvccPath"
-        $CmakeArgs += '-DGGML_CUDA_FA_ALL_QUANTS=ON'
-        $CmakeArgs += '-DGGML_CUDA_F16=OFF'
-        $CmakeArgs += '-DGGML_CUDA_GRAPHS=OFF'
-        $CmakeArgs += '-DGGML_CUDA_FORCE_CUBLAS=OFF'
-        $CmakeArgs += '-DGGML_CUDA_PEER_MAX_BATCH_SIZE=8192'
-        if ($CudaArch) {
-            # Validate nvcc actually supports this architecture
-            if (Test-NvccArchSupport -NvccExe $NvccPath -Arch $CudaArch) {
-                $CmakeArgs += "-DCMAKE_CUDA_ARCHITECTURES=$CudaArch"
-            } else {
-                # GPU arch too new for this toolkit — fall back to highest supported.
-                # PTX forward-compatibility will JIT-compile for the actual GPU at runtime.
-                $maxArch = Get-NvccMaxArch -NvccExe $NvccPath
-                if ($maxArch) {
-                    $CmakeArgs += "-DCMAKE_CUDA_ARCHITECTURES=$maxArch"
-                    Write-Host "   [WARN] GPU is sm_$CudaArch but nvcc only supports up to sm_$maxArch" -ForegroundColor Yellow
-                    Write-Host "          Building with sm_$maxArch (PTX will JIT for your GPU at runtime)" -ForegroundColor Yellow
+        # CUDA flags -- only if GPU available, otherwise explicitly disable
+        if ($HasNvidiaSmi -and $NvccPath) {
+            $CmakeArgs += '-DGGML_CUDA=ON'
+            $CmakeArgs += "-DCUDAToolkit_ROOT=$CudaToolkitRoot"
+            $CmakeArgs += "-DCUDA_TOOLKIT_ROOT_DIR=$CudaToolkitRoot"
+            $CmakeArgs += "-DCMAKE_CUDA_COMPILER=$NvccPath"
+            if ($CudaArch) {
+                # Validate nvcc actually supports this architecture
+                if (Test-NvccArchSupport -NvccExe $NvccPath -Arch $CudaArch) {
+                    $CmakeArgs += "-DCMAKE_CUDA_ARCHITECTURES=$CudaArch"
+                } else {
+                    # GPU arch too new for this toolkit -- fall back to highest supported.
+                    # PTX forward-compatibility will JIT-compile for the actual GPU at runtime.
+                    $maxArch = Get-NvccMaxArch -NvccExe $NvccPath
+                    if ($maxArch) {
+                        $CmakeArgs += "-DCMAKE_CUDA_ARCHITECTURES=$maxArch"
+                        Write-Host "   [WARN] GPU is sm_$CudaArch but nvcc only supports up to sm_$maxArch" -ForegroundColor Yellow
+                        Write-Host "          Building with sm_$maxArch (PTX will JIT for your GPU at runtime)" -ForegroundColor Yellow
+                    }
+                    # else: omit flag entirely, let cmake pick defaults
                 }
-                # else: omit flag entirely, let cmake pick defaults
             }
+        } else {
+            $CmakeArgs += '-DGGML_CUDA=OFF'
         }
 
-        cmake @CmakeArgs 2>&1 | Out-Null
+        $cmakeOutput = cmake @CmakeArgs 2>&1 | Out-String
         if ($LASTEXITCODE -ne 0) {
             $BuildOk = $false
             $FailedStep = "cmake configure"
+            Write-Host $cmakeOutput -ForegroundColor Red
+            if ($cmakeOutput -match 'No CUDA toolset found|CUDA_TOOLKIT_ROOT_DIR|nvcc') {
+                Write-Host ""
+                Write-Host "   Hint: CUDA VS integration may be missing. Try running as admin:" -ForegroundColor Yellow
+                Write-Host "   Copy contents of:" -ForegroundColor Yellow
+                Write-Host "     <CUDA_PATH>\extras\visual_studio_integration\MSBuildExtensions" -ForegroundColor Yellow
+                Write-Host "   into:" -ForegroundColor Yellow
+                Write-Host "     <VS_PATH>\MSBuild\Microsoft\VC\v170\BuildCustomizations" -ForegroundColor Yellow
+            }
         }
     }
 
@@ -1110,10 +1315,11 @@ if (Test-Path $LlamaServerBin) {
         Write-Host "   Parallel jobs: $NumCpu" -ForegroundColor Gray
         Write-Host ""
 
-        cmake --build $BuildDir --config Release --target llama-server -j $NumCpu 2>&1 | Out-Null
+        $output = cmake --build $BuildDir --config Release --target llama-server -j $NumCpu 2>&1 | Out-String
         if ($LASTEXITCODE -ne 0) {
             $BuildOk = $false
             $FailedStep = "cmake build (llama-server)"
+            Write-Host $output -ForegroundColor Red
         }
     }
 
@@ -1121,9 +1327,10 @@ if (Test-Path $LlamaServerBin) {
     if ($BuildOk) {
         Write-Host ""
         Write-Host "--- cmake build (llama-quantize) ---" -ForegroundColor Cyan
-        cmake --build $BuildDir --config Release --target llama-quantize -j $NumCpu 2>&1 | Out-Null
+        $output = cmake --build $BuildDir --config Release --target llama-quantize -j $NumCpu 2>&1 | Out-String
         if ($LASTEXITCODE -ne 0) {
             Write-Host "   [WARN] llama-quantize build failed (GGUF export may be unavailable)" -ForegroundColor Yellow
+            Write-Host $output -ForegroundColor Yellow
         }
     }
 
diff --git a/studio/setup.sh b/studio/setup.sh
index 4c8a6c7dde..bc9b563be1 100755
--- a/studio/setup.sh
+++ b/studio/setup.sh
@@ -41,13 +41,26 @@ if [[ "$keynames" == *$'\nCOLAB_'* ]]; then
 fi
 
 # ── Detect whether frontend needs building ──
-# Only skip when BOTH conditions are true:
-#   1. We're inside site-packages (PyPI / pip install, not editable)
-#   2. dist/ already exists (pre-built in the wheel)
-# Otherwise always (re)build — handles upgrades, editable installs, and
-# pip-from-source where dist/ was never built.
-if [[ "$SCRIPT_DIR" == */site-packages/* ]] && [ -d "$SCRIPT_DIR/frontend/dist" ]; then
-    echo "✅ Frontend pre-built (PyPI) — skipping Node/npm check."
+# Skip if dist/ exists AND no tracked input is newer than dist/.
+# Checks top-level config/entry files and src/, public/ recursively.
+# This handles: PyPI installs (dist/ bundled), repeat runs (no changes),
+# and upgrades/pulls (source newer than dist/ triggers rebuild).
+_NEED_FRONTEND_BUILD=true
+if [ -d "$SCRIPT_DIR/frontend/dist" ]; then
+    # Check all top-level files (package.json, bun.lock, vite.config.ts, index.html, etc.)
+    _changed=$(find "$SCRIPT_DIR/frontend" -maxdepth 1 -type f \
+        -newer "$SCRIPT_DIR/frontend/dist" -print -quit 2>/dev/null)
+    # Check src/ and public/ recursively (|| true guards against set -e when dirs are missing)
+    if [ -z "$_changed" ]; then
+        _changed=$(find "$SCRIPT_DIR/frontend/src" "$SCRIPT_DIR/frontend/public" \
+            -type f -newer "$SCRIPT_DIR/frontend/dist" -print -quit 2>/dev/null) || true
+    fi
+    if [ -z "$_changed" ]; then
+        _NEED_FRONTEND_BUILD=false
+    fi
+fi
+if [ "$_NEED_FRONTEND_BUILD" = false ]; then
+    echo "✅ Frontend already built and up to date -- skipping Node/npm check."
 else
 NEED_NODE=true
 if command -v node &>/dev/null && command -v npm &>/dev/null; then
@@ -146,12 +159,17 @@ run_quiet "npm run build" npm run build
 
 _restore_gitignores
 trap - EXIT
-cd "$SCRIPT_DIR/backend/core/data_recipe/oxc-validator"
-run_quiet "npm install (oxc validator runtime)" npm install
 cd "$SCRIPT_DIR"
 echo "✅ Frontend built to frontend/dist"
 
-fi  # end frontend dist check
+fi  # end frontend build check
+
+# ── oxc-validator runtime (needs npm -- skip if not available) ──
+if [ -d "$SCRIPT_DIR/backend/core/data_recipe/oxc-validator" ] && command -v npm &>/dev/null; then
+    cd "$SCRIPT_DIR/backend/core/data_recipe/oxc-validator"
+    run_quiet "npm install (oxc validator runtime)" npm install
+    cd "$SCRIPT_DIR"
+fi
 
 # ── 6. Python venv + deps ──
 
@@ -223,50 +241,76 @@ install_python_stack() {
     python "$SCRIPT_DIR/install_python_stack.py"
 }
 
-if [ "$IS_COLAB" = true ]; then
-    # Colab: install packages directly without venv
-    install_python_stack
-else
-    # Local: create venv under ~/.unsloth/studio/ (shared location, not in repo)
-    STUDIO_HOME="$HOME/.unsloth/studio"
-    VENV_DIR="$STUDIO_HOME/.venv"
-    VENV_T5_DIR="$STUDIO_HOME/.venv_t5"
-    mkdir -p "$STUDIO_HOME"
+# Create venv under ~/.unsloth/studio/ (shared location, not in repo).
+# All platforms (including Colab) use the same isolated venv so that
+# studio dependencies are never installed into the system Python.
+STUDIO_HOME="$HOME/.unsloth/studio"
+VENV_DIR="$STUDIO_HOME/.venv"
+VENV_T5_DIR="$STUDIO_HOME/.venv_t5"
+mkdir -p "$STUDIO_HOME"
 
-    # Clean up legacy in-repo venvs if they exist
-    [ -d "$REPO_ROOT/.venv" ] && rm -rf "$REPO_ROOT/.venv"
-    [ -d "$REPO_ROOT/.venv_overlay" ] && rm -rf "$REPO_ROOT/.venv_overlay"
-    [ -d "$REPO_ROOT/.venv_t5" ] && rm -rf "$REPO_ROOT/.venv_t5"
+# Clean up legacy in-repo venvs if they exist
+[ -d "$REPO_ROOT/.venv" ] && rm -rf "$REPO_ROOT/.venv"
+[ -d "$REPO_ROOT/.venv_overlay" ] && rm -rf "$REPO_ROOT/.venv_overlay"
+[ -d "$REPO_ROOT/.venv_t5" ] && rm -rf "$REPO_ROOT/.venv_t5"
 
-    rm -rf "$VENV_DIR"
-    rm -rf "$VENV_T5_DIR"
-    "$BEST_PY" -m venv "$VENV_DIR"
+rm -rf "$VENV_DIR"
+rm -rf "$VENV_T5_DIR"
+# Try creating venv with pip; fall back to --without-pip + bootstrap
+# (some environments like Colab have broken ensurepip)
+if ! "$BEST_PY" -m venv "$VENV_DIR" 2>/dev/null; then
+    "$BEST_PY" -m venv --without-pip "$VENV_DIR"
     source "$VENV_DIR/bin/activate"
-    cd "$SCRIPT_DIR"
-    install_python_stack
+    curl -sS https://bootstrap.pypa.io/get-pip.py | python > /dev/null
+else
+    source "$VENV_DIR/bin/activate"
+fi
 
-    # ── 6b. Pre-install transformers 5.x into .venv_t5/ ──
-    # Models like GLM-4.7-Flash need transformers>=5.3.0. Instead of pip-installing
-    # at runtime (slow, ~10-15s), we pre-install into a separate directory.
-    # The training subprocess just prepends .venv_t5/ to sys.path — instant switch.
-    echo ""
-    echo "   Pre-installing transformers 5.x for newer model support..."
-    mkdir -p "$VENV_T5_DIR"
-    run_quiet "pip install transformers 5.x" pip install --target "$VENV_T5_DIR" --no-deps "transformers==5.3.0"
-    run_quiet "pip install huggingface_hub for t5" pip install --target "$VENV_T5_DIR" --no-deps "huggingface_hub==1.3.0"
-    echo "✅ Transformers 5.x pre-installed to $VENV_T5_DIR/"
+# ── Ensure uv is available (much faster than pip) ──
+USE_UV=false
+if command -v uv &>/dev/null; then
+    USE_UV=true
+elif curl -LsSf https://astral.sh/uv/install.sh | sh > /dev/null 2>&1; then
+    export PATH="$HOME/.local/bin:$PATH"
+    command -v uv &>/dev/null && USE_UV=true
+fi
 
-    # ── 7. WSL: pre-install GGUF build dependencies ──
-    # On WSL, sudo requires a password and can't be entered during GGUF export
-    # (runs in a non-interactive subprocess). Install build deps here instead.
-    if grep -qi microsoft /proc/version 2>/dev/null; then
-        echo ""
-        echo "⚠️  WSL detected — installing build dependencies for GGUF export..."
-        echo "   You may be prompted for your password."
-        sudo apt-get update -y
-        sudo apt-get install -y build-essential cmake curl git libcurl4-openssl-dev
-        echo "✅ GGUF build dependencies installed"
+# Helper: install a package, preferring uv with pip fallback
+fast_install() {
+    if [ "$USE_UV" = true ]; then
+        uv pip install --python "$(command -v python)" "$@" && return 0
     fi
+    python -m pip install "$@"
+}
+
+cd "$SCRIPT_DIR"
+install_python_stack
+
+# ── 6b. Pre-install transformers 5.x into .venv_t5/ ──
+# Models like GLM-4.7-Flash need transformers>=5.3.0. Instead of pip-installing
+# at runtime (slow, ~10-15s), we pre-install into a separate directory.
+# The training subprocess just prepends .venv_t5/ to sys.path -- instant switch.
+echo ""
+echo "   Pre-installing transformers 5.x for newer model support..."
+mkdir -p "$VENV_T5_DIR"
+run_quiet "install transformers 5.x" fast_install --target "$VENV_T5_DIR" --no-deps "transformers==5.3.0"
+run_quiet "install huggingface_hub for t5" fast_install --target "$VENV_T5_DIR" --no-deps "huggingface_hub==1.7.1"
+run_quiet "install hf_xet for t5" fast_install --target "$VENV_T5_DIR" --no-deps "hf_xet==1.4.2"
+# tiktoken is needed by Qwen-family tokenizers. Install with deps since
+# regex/requests may be missing on Windows.
+run_quiet "install tiktoken for t5" fast_install --target "$VENV_T5_DIR" "tiktoken"
+echo "✅ Transformers 5.x pre-installed to $VENV_T5_DIR/"
+
+# ── 7. WSL: pre-install GGUF build dependencies ──
+# On WSL, sudo requires a password and can't be entered during GGUF export
+# (runs in a non-interactive subprocess). Install build deps here instead.
+if grep -qi microsoft /proc/version 2>/dev/null; then
+    echo ""
+    echo "⚠️  WSL detected -- installing build dependencies for GGUF export..."
+    echo "   You may be prompted for your password."
+    sudo apt-get update -y
+    sudo apt-get install -y build-essential cmake curl git libcurl4-openssl-dev
+    echo "✅ GGUF build dependencies installed"
 fi
 
 # ── 8. Build llama.cpp binaries for GGUF inference + export ──
@@ -405,6 +449,9 @@ if [ "$IS_COLAB" = true ]; then
     echo "╠══════════════════════════════════════╣"
     echo "║ Unsloth Studio is ready to start     ║"
     echo "║ in your Colab notebook!              ║"
+    echo "║                                      ║"
+    echo "║ from colab import start              ║"
+    echo "║ start()                              ║"
     echo "╚══════════════════════════════════════╝"
 else
     echo "╔══════════════════════════════════════╗"