宋小猫

SongXiaoMao's activity

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

New activity in halt95/Qwen3.8-Flash-Next-W4A16-Merlin 12 days ago

Thank you so much for the quantization and for open-sourcing this!

❤️ 2

4

#3 opened 13 days ago by

SongXiaoMao

New activity in albucino/Qwen3.8-Flash-Next-W4A16-FP8PLE 29 days ago

VLLM startup error

4

#2 opened 29 days ago by

SongXiaoMao

New activity in VnimanieAI/Qwen3.8-Flash-Next-W4A16 about 1 month ago

ways to squeeze more context?

4

#3 opened about 1 month ago by

SageHusky

New activity in aixiaoma/Qwen3.8-Flash-Next-W4A16 about 1 month ago

Thanks for the model and 3090GPU launch code

#2 opened about 1 month ago by

SongXiaoMao

New activity in Inferact/Qwen3.8-Flash-Next-NVFP4 about 1 month ago

Is 180GB right?

10

#1 opened about 1 month ago by

sisfabc

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B about 2 months ago

New Model based on Qwen 3.8

➕🔥 27

18

#23 opened 2 months ago by

jaskfsafdjlk

New activity in nerkyor/Qwen3.6-27B-DSV4Pro-Thinking-Distill 3 months ago

VLLM启动报错

9

#2 opened 4 months ago by

SongXiaoMao

New activity in havenoammo/Qwen3.6-27B-INT8-MTP 5 months ago

MTP efficiency without official FP8 ha

👍 1

#1 opened 5 months ago by

SongXiaoMao

New activity in nameistoken/Qwen3.6-27B-Quark-W8A8-INT8 5 months ago

MTP cannot be accelerated

#1 opened 5 months ago by

SongXiaoMao

New activity in inclusionAI/Ling-2.6-flash-int4 5 months ago

The official VLLM example starts normal inference error

#3 opened 5 months ago by

SongXiaoMao

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

This model cannot use MTP

4

#2 opened 6 months ago by

SongXiaoMao

Modify the configuration file

🔥 1

1

#1 opened 6 months ago by

SongXiaoMao

New activity in z-lab/Qwen3.5-27B-DFlash 6 months ago

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

17

#2 opened 6 months ago by

unoid

New activity in Jackrong/Qwopus3.5-27B-v3 6 months ago

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

😔 3

7

#8 opened 6 months ago by

beginor

New activity in olka-fi/Qwen3.5-27B-MXFP4 6 months ago

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

#3 opened 6 months ago by

SongXiaoMao

New activity in Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled 6 months ago

How does the VLLM start this model?

2

#4 opened 7 months ago by

SongXiaoMao

New activity in olka-fi/Qwen3.5-122B-A10B-MXFP4 6 months ago

This quantization model is amzing

👍❤️ 2

5

#1 opened 7 months ago by

hyunw55

New activity in olka-fi/Qwen3.5-27B-MXFP4 6 months ago

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

3

#2 opened 6 months ago by

SongXiaoMao

New activity in edp1096/Huihui-Qwen3.5-27B-abliterated-FP8 6 months ago

Sensitive information is not a question

2

#3 opened 6 months ago by

SongXiaoMao

New activity in win10/Huihui-Qwen3.5-27B-abliterated-FP8 6 months ago

VLLM 0.18.0 runs with an error

#2 opened 6 months ago by

SongXiaoMao