JunHowie
JunHowie
AI & ML interests
None yet
Recent Activity
new activity about 9 hours ago
QuantTrio/Qwen3.6-35B-A3B-AWQ:Very good quality tested. On par with Qwen3.5-27b-awq. lot's of thank to QuantTrio updated a model about 16 hours ago
QuantTrio/Qwen3.6-35B-A3B-AWQ updated a model about 17 hours ago
QuantTrio/gemma-4-31B-it-AWQOrganizations
Very good quality tested. On par with Qwen3.5-27b-awq. lot's of thank to QuantTrio
2
#2 opened about 9 hours ago
by
kq
Would be great to have 6bit AWQ with repaired tensors.
1
#1 opened 3 days ago
by
slavap5
[Request] Great work! Do you have plans to also create GLM-5.1-AWQ?
🤗 1
7
#6 opened 10 days ago
by
ag1988
QuantTrio/MiniMax-M2.7-AWQ release?
👍 1
1
#3 opened 5 days ago
by
sigbjobo
This is the best quant version in the world,better than FP8
🚀 5
4
#2 opened about 1 month ago
by
kq
Update chat_template.jinja according to upstream google official repository
1
#2 opened 7 days ago
by
dayvidwelles
vllm部署失败
6
#3 opened about 1 month ago
by
Yuxin362
Do you take quant requests?
1
#1 opened about 1 month ago
by
pathosethoslogos
why cuda12.8 needed?
1
#1 opened about 1 month ago
by
justplus
--max-model-len 32768 seems a bit too small for agent use cases ?
3
#3 opened about 1 month ago
by
edwarddukewu
AWQ
🤝 3
1
#3 opened 2 months ago
by
darkstar3537
Great work
5
#1 opened about 2 months ago
by
JoeyHwong
Qwen3.5-397B-A17B-AWQ vs Qwen3.5-122B-A10B
2
#2 opened about 2 months ago
by
zuuky
Kimi-K2.5-E192 ?
1
#2 opened 2 months ago
by
Rebis
Qwen3.5 AWQ 4 Bit
2
#1 opened about 2 months ago
by
yuchenxie
Qwen3.5 AWQ
1
#3 opened about 2 months ago
by
timroethig
MiniMax-M2.5-AWQ please
🔥 1
3
#3 opened 2 months ago
by
olka-fi
Once again Thanks, here is my review for 8 x RTX 5090 setup
17
#2 opened 4 months ago
by
crystech