RedHatAI
/

Qwen3-32B-NVFP4

Text Generation

8-bit precision

compressed-tensors

Model card Files Files and versions

nm-research commited on 1 day ago

Commit

fe51976

·

verified ·

1 Parent(s): 3ccfb74

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -348,7 +348,7 @@ lm_eval \
 # --- model_args.yaml ---
 cat > model_args.yaml <<'YAML'
 model_parameters:
-  model_name: "RedHatAI/Qwen3-8B-NVFP4"
   dtype: auto
   gpu_memory_utilization: 0.9
   tensor_parallel_size: 2

 # --- model_args.yaml ---
 cat > model_args.yaml <<'YAML'
 model_parameters:
+  model_name: "RedHatAI/Qwen3-32B-NVFP4"
   dtype: auto
   gpu_memory_utilization: 0.9
   tensor_parallel_size: 2