diff --git a/studio/backend/core/inference/diffusion_transformer_quant.py b/studio/backend/core/inference/diffusion_transformer_quant.py
index 6929130034..f60940c4ed 100644
--- a/studio/backend/core/inference/diffusion_transformer_quant.py
+++ b/studio/backend/core/inference/diffusion_transformer_quant.py
@@ -77,13 +77,15 @@ _DATACENTER_GPU_TOKENS = frozenset(
     {
         "B200",
         "B100",
+        "B300",  # Blackwell Ultra data center
         "GB200",
         "GB300",
         "GB10",  # Blackwell data center
         "H200",
         "H100",
         "H800",
-        "H20",  # Hopper data center
+        "H20",
+        "GH200",  # Grace-Hopper superchip (data center)
         "A100",
         "A800",
         "A30",
diff --git a/studio/backend/tests/test_diffusion_transformer_quant.py b/studio/backend/tests/test_diffusion_transformer_quant.py
index 83530d4d93..d527723b2e 100644
--- a/studio/backend/tests/test_diffusion_transformer_quant.py
+++ b/studio/backend/tests/test_diffusion_transformer_quant.py
@@ -279,6 +279,8 @@ def test_is_consumer_gpu_true(monkeypatch, name):
     "name",
     [
         "NVIDIA B200",
+        "NVIDIA B300",  # Blackwell Ultra (matches llama_cpp datacenter regex)
+        "NVIDIA GH200 480GB",  # Grace-Hopper superchip (was misread as consumer)
         "NVIDIA H100 80GB HBM3",
         "NVIDIA A100-SXM4-80GB",
         "NVIDIA A40",  # data-center Ampere (distinct token from RTX A4000)