lukealonso
/

MiniMax-M2-NVFP4

8-bit precision

Model card Files Files and versions

lukealonso commited on Nov 7, 2025

Commit

27044df

·

verified ·

1 Parent(s): 7fd9221

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -6,7 +6,7 @@ base_model:
 modelopt quantized NVFP4 MiniMax-M2
 Tested on 2x RTX Pro 6000 Blackwell
  inference:
     image: vllm/vllm-openai:nightly
     container_name: inference
@@ -57,4 +57,5 @@ Tested on 2x RTX Pro 6000 Blackwell
       - --host
       - "0.0.0.0"
       - --port
-      - "8000"

 modelopt quantized NVFP4 MiniMax-M2
 Tested on 2x RTX Pro 6000 Blackwell
+```
  inference:
     image: vllm/vllm-openai:nightly
     container_name: inference
       - --host
       - "0.0.0.0"
       - --port
+      - "8000"
+```