Hugging Face's logo

lukealonso
/
MiniMax-M2.1-NVFP4

Safetensors
minimax_m2
custom_code
8-bit precision
modelopt
Model card Files
xet
Community
3
lukealonso commited on
Commit
0abca8e
·
verified ·
1 Parent(s): 55443c9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -5,9 +5,7 @@ base_model:
5
 
6
  modelopt NVFP4 quantized MiniMax-M2.1
7
 
8
- Not yet extensively tested, but does appear to work fine on 2x and 4x RTX 6000 Pro Blackwell via vLLM.
9
-
10
- If you see "No available shared memory broadcast block found in 60 seconds.", be patient.
11
 
12
  Sample docker run (you will want to change this so it's not downloading the model repeatedly by mounting in your HF cache dir):
13
 
 
5
 
6
  modelopt NVFP4 quantized MiniMax-M2.1
7
 
8
+ Works fine on 2x and 4x RTX 6000 Pro Blackwell via vLLM.
 
 
9
 
10
  Sample docker run (you will want to change this so it's not downloading the model repeatedly by mounting in your HF cache dir):
11