宋小猫

SongXiaoMao's activity

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

New activity in havenoammo/Qwen3.6-27B-INT8-MTP about 3 hours ago

MTP efficiency without official FP8 ha

👍 1

#1 opened about 3 hours ago by

SongXiaoMao

liked a model about 3 hours ago

havenoammo/Qwen3.6-27B-INT8-MTP

Image-Text-to-Text • 28B • Updated 11 days ago • 1.75k • 3

New activity in nameistoken/Qwen3.6-27B-Quark-W8A8-INT8 3 days ago

MTP cannot be accelerated

#1 opened 3 days ago by

SongXiaoMao

New activity in inclusionAI/Ling-2.6-flash-int4 20 days ago

The official VLLM example starts normal inference error

#3 opened 20 days ago by

SongXiaoMao

New activity in groxaxo/Qwen3.6-27B-GPTQ-Pro-4bit 26 days ago

This model cannot use MTP

3

#2 opened 27 days ago by

SongXiaoMao

New activity in groxaxo/Qwen3.6-27B-GPTQ-Pro-4bit 27 days ago

Modify the configuration file

🔥 1

1

#1 opened 27 days ago by

SongXiaoMao

liked a model about 1 month ago

huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated

Image-Text-to-Text • 36B • Updated Apr 18 • 20.6k • 52

New activity in z-lab/Qwen3.5-27B-DFlash about 1 month ago

FP8 work for base model or is 16-bit of 27B required?

14

#2 opened about 2 months ago by

unoid

liked 2 models about 1 month ago

Qwen/Qwen3.5-27B-FP8

Image-Text-to-Text • 28B • Updated 26 days ago • 2.05M • 133

Qwen/Qwen3.5-122B-A10B-GPTQ-Int4

Image-Text-to-Text • 125B • Updated 26 days ago • 76k • 37

New activity in Jackrong/Qwopus3.5-27B-v3 about 2 months ago

Is there anyone who can tell me how to run this model with vllm correctly?

😔 3

7

#8 opened about 2 months ago by

beginor

New activity in olka-fi/Qwen3.5-27B-MXFP4 about 2 months ago

Can the big guy quantify this model into MXFP4? Thank you!!

#3 opened about 2 months ago by

SongXiaoMao

New activity in Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled about 2 months ago

How does the VLLM start this model?

2

#4 opened 2 months ago by

SongXiaoMao

New activity in olka-fi/Qwen3.5-122B-A10B-MXFP4 about 2 months ago

This quantization model is amzing

❤️👍 2

5

#1 opened 2 months ago by

hyunw55

New activity in olka-fi/Qwen3.5-27B-MXFP4 about 2 months ago

Why is the file size of 4bit similar to FP8?

3

#2 opened about 2 months ago by

SongXiaoMao

liked 2 models about 2 months ago

olka-fi/Qwen3.5-35B-A3B-MXFP4

Image-Text-to-Text • 20B • Updated Mar 15 • 91 • 2

olka-fi/Qwen3.5-122B-A10B-MXFP4

Text Generation • 71B • Updated Feb 25 • 513 • 10

New activity in edp1096/Huihui-Qwen3.5-27B-abliterated-FP8 about 2 months ago

Sensitive information is not a question

2

#3 opened about 2 months ago by

SongXiaoMao

New activity in win10/Huihui-Qwen3.5-27B-abliterated-FP8 about 2 months ago

VLLM 0.18.0 runs with an error

#2 opened about 2 months ago by

SongXiaoMao

New activity in groxaxo/Huihui-Qwen3.5-27B-W8A8-INT8 about 2 months ago

I get an error using vllm0.18.0

1

#1 opened about 2 months ago by

SongXiaoMao