JunHowie

JunHowie's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in QuantTrio/GLM-5.2-Int4-Int8Mix about 11 hours 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

1

#3 opened about 14 hours ago by

kinggenguo

New activity in QuantTrio/GLM-5.2-Int4-Int8Mix 7 days ago

Any chances for A100?

4

#1 opened 7 days ago by

traphix

New activity in QuantTrio/GLM-5.1-AWQ 9 days ago

GLM-5.2-AWQ

1

#2 opened 14 days ago by

ag1988

New activity in QuantTrio/GLM-5-AWQ 2 months ago

[Request] Great work! Do you have plans to also create GLM-5.1-AWQ?

🤗 1

10

#6 opened 3 months ago by

ag1988

New activity in QuantTrio/Qwen3.6-35B-A3B-AWQ 2 months ago

Very good quality tested. On par with Qwen3.5-27b-awq. lot's of thank to QuantTrio

3

#2 opened 2 months ago by

kq

New activity in QuantTrio/Qwopus3.5-27B-v3-AWQ-6Bit 2 months ago

Would be great to have 6bit AWQ with repaired tensors.

2

#1 opened 3 months ago by

slavap5

New activity in QuantTrio/Qwen3.5-27B-AWQ 2 months ago

Request for AWQ Quant of Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-i1

1

#6 opened 3 months ago by

celikburak

New activity in QuantTrio/MiniMax-M2.5-AWQ 2 months ago

QuantTrio/MiniMax-M2.7-AWQ release?

👍 1

1

#3 opened 3 months ago by

sigbjobo

New activity in QuantTrio/Qwen3.5-27B-AWQ 2 months ago

This is the best quant version in the world,better than FP8

🚀 5

4

#2 opened 4 months ago by

kq

New activity in QuantTrio/gemma-4-31B-it-AWQ-6Bit 2 months ago

Update chat_template.jinja according to upstream google official repository

1

#2 opened 3 months ago by

dayvidwelles

New activity in QuantTrio/GLM-5-AWQ 3 months ago

vllm部署失败

6

#3 opened 4 months ago by

Yuxin362

New activity in QuantTrio/sarvam-105b-AWQ 3 months ago

Do you take quant requests?

1

#1 opened 4 months ago by

pathosethoslogos

New activity in QuantTrio/Qwen3.5-9B-AWQ 3 months ago

why cuda12.8 needed?

1

#1 opened 3 months ago by

justplus

New activity in QuantTrio/Qwen3.5-27B-AWQ 4 months ago

--max-model-len 32768 seems a bit too small for agent use cases ?

3

#3 opened 4 months ago by

edwarddukewu

New activity in arcee-ai/Trinity-Large-Preview 4 months ago

AWQ

🤝 3

1

#3 opened 5 months ago by

darkstar3537

New activity in QuantTrio/GLM-5-AWQ 4 months ago

Great work

5

#1 opened 4 months ago by

JoeyHwong

New activity in QuantTrio/Qwen3.5-397B-A17B-AWQ 4 months ago

Qwen3.5-397B-A17B-AWQ vs Qwen3.5-122B-A10B

2

#2 opened 4 months ago by

zuuky

New activity in QuantTrio/Kimi-K2.5-E304 4 months ago

Kimi-K2.5-E192 ?

1

#2 opened 5 months ago by

Rebis

New activity in QuantTrio/MiniMax-M2.5-AWQ 4 months ago

Qwen3.5 AWQ 4 Bit

2

#1 opened 4 months ago by

yuchenxie

New activity in QuantTrio/Qwen3-VL-235B-A22B-Thinking-AWQ 4 months ago

Qwen3.5 AWQ

1

#3 opened 4 months ago by

timroethig