From ee86530e55ea98e060fb9c86f0bf3f5a48f61238 Mon Sep 17 00:00:00 2001
From: Lee Jackson <130007945+Imagineer99@users.noreply.github.com>
Date: Thu, 16 Apr 2026 19:27:30 +0100
Subject: [PATCH] chore: switch helper and no-cache fallback to Gemma (#5066)

---
 studio/backend/utils/datasets/llm_assist.py      |  2 +-
 .../src/features/chat/api/chat-adapter.ts        | 16 ++++++++--------
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/studio/backend/utils/datasets/llm_assist.py b/studio/backend/utils/datasets/llm_assist.py
index fdc4f374ab..4c66d2ebf6 100644
--- a/studio/backend/utils/datasets/llm_assist.py
+++ b/studio/backend/utils/datasets/llm_assist.py
@@ -26,7 +26,7 @@ from loggers import get_logger
 
 logger = get_logger(__name__)
 
-DEFAULT_HELPER_MODEL_REPO = "unsloth/Qwen3.5-4B-GGUF"
+DEFAULT_HELPER_MODEL_REPO = "unsloth/gemma-4-E2B-it-GGUF"
 DEFAULT_HELPER_MODEL_VARIANT = "UD-Q4_K_XL"
 
 README_MAX_CHARS = 1500
diff --git a/studio/frontend/src/features/chat/api/chat-adapter.ts b/studio/frontend/src/features/chat/api/chat-adapter.ts
index 60904f3cb5..53a935cf45 100644
--- a/studio/frontend/src/features/chat/api/chat-adapter.ts
+++ b/studio/frontend/src/features/chat/api/chat-adapter.ts
@@ -455,13 +455,13 @@ async function autoLoadSmallestModel(): Promise<{
     // No cached models found — try downloading a small default GGUF
     toast("Downloading a small model…", {
       id: toastId,
-      description: "No downloaded models found. Fetching Qwen3.5-4B (UD-Q4_K_XL).",
+      description: "No downloaded models found. Fetching Gemma-4-E2B-it (UD-Q4_K_XL).",
       duration: 30000,
     });
     try {
       if (
         !(await canAutoLoad({
-          model_path: "unsloth/Qwen3.5-4B-GGUF",
+          model_path: "unsloth/gemma-4-E2B-it-GGUF",
           max_seq_length: 0,
           is_lora: false,
           gguf_variant: "UD-Q4_K_XL",
@@ -471,7 +471,7 @@ async function autoLoadSmallestModel(): Promise<{
         return { loaded: false, blockedByTrustRemoteCode };
       }
       const loadResp = await loadModel({
-        model_path: "unsloth/Qwen3.5-4B-GGUF",
+        model_path: "unsloth/gemma-4-E2B-it-GGUF",
         hf_token: hfToken,
         max_seq_length: 0,
         load_in_4bit: true,
@@ -479,20 +479,20 @@ async function autoLoadSmallestModel(): Promise<{
         gguf_variant: "UD-Q4_K_XL",
         trust_remote_code: trustRemoteCode,
       });
-      useChatRuntimeStore.getState().setCheckpoint("unsloth/Qwen3.5-4B-GGUF", "UD-Q4_K_XL");
+      useChatRuntimeStore.getState().setCheckpoint("unsloth/gemma-4-E2B-it-GGUF", "UD-Q4_K_XL");
       const store = useChatRuntimeStore.getState();
       store.setModelRequiresTrustRemoteCode(
         loadResp.requires_trust_remote_code ?? false,
       );
       store.setParams({ ...store.params, maxTokens: loadResp.context_length ?? 131072 });
       const defaultModel: ChatModelSummary = {
-        id: "unsloth/Qwen3.5-4B-GGUF",
-        name: loadResp.display_name ?? "Qwen3.5-4B-GGUF",
+        id: "unsloth/gemma-4-E2B-it-GGUF",
+        name: loadResp.display_name ?? "gemma-4-E2B-it-GGUF",
         isVision: loadResp.is_vision ?? false,
         isLora: false,
         isGguf: true,
       };
-      if (!store.models.some((m) => m.id === "unsloth/Qwen3.5-4B-GGUF")) {
+      if (!store.models.some((m) => m.id === "unsloth/gemma-4-E2B-it-GGUF")) {
         store.setModels([...store.models, defaultModel]);
       }
       useChatRuntimeStore.setState({
@@ -509,7 +509,7 @@ async function autoLoadSmallestModel(): Promise<{
         defaultChatTemplate: loadResp.chat_template ?? null,
         chatTemplateOverride: null,
       });
-      toast.success("Loaded Qwen3.5-4B (UD-Q4_K_XL)", { id: toastId });
+      toast.success("Loaded Gemma-4-E2B-it (UD-Q4_K_XL)", { id: toastId });
       return { loaded: true, blockedByTrustRemoteCode: false };
     } catch {
       toast.dismiss(toastId);