RedHatAI/gemma-4-31B-it-FP8-block
Image-Text-to-Text • 31B • Updated • 44.2k • 14
DD
weisunding
AI & ML interests
None yet
Recent Activity
new activity about 5 hours ago
MiniMaxAI/MiniMax-M2.7:Running MiniMax M2.7 based on VLLM, the longer it runs, the dumber the model feels. new activity 3 days ago
MiniMaxAI/MiniMax-M2.7:MiniMax-M2.7 is highly verbose and slow new activity 5 days ago
TeichAI/gemma-4-31B-it-Claude-Opus-Distill-GGUF:LLM performance is unstableOrganizations
None yet
Running MiniMax M2.7 based on VLLM, the longer it runs, the dumber the model feels.
👍 5
6
#20 opened 2 days ago
by 
wolfzr
MiniMax-M2.7 is highly verbose and slow
2
#18 opened 3 days ago
by weisunding
LLM performance is unstable
6
#6 opened 5 days ago
by weisunding
Inference is slow with A100
1
#3 opened 5 days ago
by weisunding
liked a
model 6 days ago