zletpm996
zletpm
AI & ML interests
AI for chemistry
Recent Activity
new activity
1 day ago
Qwen/Qwen3.5-397B-A17B:Suggestion: Dense versions of Qwen 3.5 at multiple scales
liked
a model
1 day ago
Qwen/Qwen3.5-397B-A17B
new activity
1 day ago
Qwen/Qwen3.5-397B-A17B-FP8:Is there possible to see 32B dense version?
Organizations
Suggestion: Dense versions of Qwen 3.5 at multiple scales
2
#31 opened 1 day ago
by
zletpm
Is there possible to see 32B dense version?
#7 opened 1 day ago
by
zletpm
This model performs worse than the Mistral-Small-3.1-24B model with a 4-bit quantization.
➕
3
2
#6 opened 8 months ago
by
zletpm
Is there a chance to get the AWQ or DWQ model? Mac Studio (512GB) has a 3-bit honey point.
👍
1
5
#1 opened 9 months ago
by
zletpm
I hope you guys can provide a 32B dense model
👍
2
#9 opened 8 months ago
by
zletpm
MLX Convert Error
4
#8 opened 8 months ago
by
baggaindia
Performance problem: 32B 4x slower than 30B
1
#27 opened 9 months ago
by
jagusztinl
Is this DWQ model converted using the default dataset “allenai/tulu-3-sft-mixture”?
#1 opened 9 months ago
by
zletpm
What distinguishes this model from another MLX-Community/Qwen3-30B-A3B-4bit-DWQ?
5
#1 opened 10 months ago
by
zletpm
I hope this project can provide more information about this model.
#1 opened 10 months ago
by
zletpm
why i can see any model file?
1
#4 opened 10 months ago
by
zletpm
Access Rejected
5
#62 opened 10 months ago
by
ansenang
access denied
👀
👍
8
1
#44 opened 11 months ago
by
qulong
Could you please provide a 16-bit version or teach me the steps involved in converting it myself
1
#1 opened 11 months ago
by
zletpm
Could you please provide a 16-bit version or teach me the steps involved in converting it myself
1
#1 opened 11 months ago
by
zletpm
Could you please provide a 16-bit version or teach me the steps involved in converting it myself
1
#1 opened 11 months ago
by
zletpm