DD
weisunding
AI & ML interests
None yet
Recent Activity
new activity 2 days ago
plunderstruck/Qwable-3.6-27B-MTP-ROCmFP4-GGUF:awsome model liked a model 3 days ago
plunderstruck/Qwable-3.6-27B-MTP-ROCmFP4-GGUFOrganizations
None yet
awsome model
#1 opened 2 days ago
by
weisunding
New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 2 days ago
Amazing fusion model
#23 opened 2 days ago
by
weisunding
New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 3 days ago
Is there a chat_template.jinja for llama-server + claude code?
1
#19 opened 3 days ago
by
weisunding
Can you fix the Qwen3.6-27B tool calling issue meanwhile?
2
#3 opened 22 days ago
by
weisunding
Qwen3.7 27B without overthinking
👍 2
6
#38 opened 2 months ago
by
Duonglv
where is 31B-Dense
👍 64
5
#9 opened 30 days ago
by
waynesjtu
31B-Dense model missing from HuggingFace
👍👀 28
15
#2 opened about 1 month ago
by
smcleod
Running MiniMax M2.7 based on VLLM, the longer it runs, the dumber the model feels.
👍 6
9
#20 opened 3 months ago
by
wolfzr
Anyone is having issues with tool calling with the 3.6 family ? (not just 35b or 27b)
4
#13 opened 3 months ago
by
LPN64
Qwen3.6-27B is suprisingly good for coding
🔥 1
1
#12 opened 3 months ago
by
weisunding
This LLM is a test maxer, not a general purpose AI model.
👍 3
21
#17 opened 3 months ago
by
phil111
tool calling failed with claude code
1
#30 opened 3 months ago
by
weisunding
MiniMax-M2.7 is highly verbose and slow
3
#18 opened 3 months ago
by
weisunding
LLM performance is unstable
6
#6 opened 4 months ago
by
weisunding
Inference is slow with A100
1
#3 opened 4 months ago
by
weisunding
LLM performance is unstable
6
#6 opened 4 months ago
by
weisunding