Hugging Face's logo

QuantTrio
Team
community
Activity Feed

AI & ML interests

We're a trio of AI enthusiasts who create LLM quantization models (GPTQ, WNA16) in our spare time. We bridge ModelScope and Hugging Face by porting our quantized models to make efficient AI more accessible globally.

Recent Activity
tclf90  new activity about 1 month ago
QuantTrio/Kimi-K3-Cubic-2.5Bit:benchmark data for Kimi-K3-Cubic-2.5Bit
tclf90  new activity about 2 months ago
QuantTrio/Kimi-K3-Cubic-2.5Bit:佈署失敗 (ó﹏ò｡)
JunHowie  updated a model about 2 months ago
QuantTrio/Kimi-K3-Cubic-2.5Bit
View all activity
tclf90 
in QuantTrio/Kimi-K3-Cubic-2.5Bit about 1 month ago

benchmark data for Kimi-K3-Cubic-2.5Bit

4
#2 opened about 2 months ago by
bencswong2
tclf90 
in QuantTrio/Kimi-K3-Cubic-2.5Bit about 2 months ago

佈署失敗 (ó﹏ò｡)

4
#4 opened about 2 months ago by
gold9450412
JunHowie 
updated a model about 2 months ago
tclf90 
in QuantTrio/Kimi-K3-Cubic-2.5Bit about 2 months ago

Roadmap for DSpark support in the Cubic vLLM branch?

2
#3 opened about 2 months ago by
bencswong2
JunHowie 
in QuantTrio/Kimi-K3-Cubic-2.5Bit about 2 months ago

啥时候上传完呀，老哥。modelscope太慢了

1
#1 opened about 2 months ago by
bencswong2
JunHowie 
published a model about 2 months ago
JunHowie 
in QuantTrio/gemma-4-31B-it-AWQ 2 months ago

Request update model to google updates of july 2026

1
#3 opened 2 months ago by
bagwani
JunHowie 
updated a model 2 months ago
tclf90 
in QuantTrio/GLM-5.2-Int4-Int8Mix 3 months ago

GLM-5.2-Int4-Int8Mix generates only "!!!!!" on H100 8×80GB with vLLM 0.23.0/0.24.0 — IndexShare sparse indexer K-cache never populated during prefill

4
#3 opened 3 months ago by
kinggenguo
JunHowie 
in QuantTrio/GLM-5.2-Int4-Int8Mix 3 months ago

GLM-5.2-Int4-Int8Mix generates only "!!!!!" on H100 8×80GB with vLLM 0.23.0/0.24.0 — IndexShare sparse indexer K-cache never populated during prefill

4
#3 opened 3 months ago by
kinggenguo
tclf90 
in QuantTrio/GLM-5.2-Int4-Int8Mix 3 months ago

AWQ 4bit

2
#2 opened 3 months ago by
MatthieuZ
JunHowie 
in QuantTrio/GLM-5.2-Int4-Int8Mix 3 months ago

Any chances for A100?

5
#1 opened 3 months ago by
traphix
JunHowie 
updated a model 3 months ago
JunHowie 
published 2 models 3 months ago
JunHowie 
updated a model 3 months ago
JunHowie 
in QuantTrio/GLM-5.1-AWQ 3 months ago

GLM-5.2-AWQ

1
#2 opened 3 months ago by
ag1988
tclf90 
in QuantTrio/GLM-4.7-AWQ 4 months ago

Revert remplate
#8 opened 4 months ago by
s-yanev

Support for structured output
#7 opened 4 months ago by
s-yanev
tclf90 
in QuantTrio/DeepSeek-V3.1-AWQ-Lite 5 months ago

Fix chat_template crash when assistant message omits the `content` key
#5 opened 5 months ago by
qgallouedec