Michael Han

shimmyshimmer's activity

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

New activity in unsloth/Qwen3.6-27B-NVFP4 13 days ago

NVFP4 vs FP8 throughput on an RTX 6000 Pro 96 GB (Blackwell) - real vLLM numbers

❤️👍 3

1

#9 opened 13 days ago by

janreges3

New activity in unsloth/DeepSeek-V4-Flash-GGUF 16 days ago

Please wait for official announcement before using!

🧠🚀 9

6

#5 opened 17 days ago by

danielhanchen

My output is garbled

4

#4 opened 17 days ago by

pliskin123

DeepSeek-V4-Flash is now ready to run locally! 🐳

❤️👍 8

18

#6 opened 16 days ago by

danielhanchen

Lower quants?

➕ 1

10

#2 opened 17 days ago by

Kelheor

New activity in unsloth/Qwen-AgentWorld-35B-A3B-GGUF 29 days ago

mmproj file so small!

7

#1 opened 29 days ago by

CHHORVORN

New activity in unsloth/GLM-5.2-GGUF about 1 month ago

Jinja2 prompt template fix to get GLM5.2 running in LM Studio and Unsloth Studio

5

#6 opened about 1 month ago by

Ackerka

New activity in unsloth/Kimi-K2.7-Code-GGUF about 1 month ago

Gibberish output IQ3_XXS

4

#4 opened about 1 month ago by

AImhotep

New activity in unsloth/Qwen3.6-27B-MTP-GGUF about 2 months ago

One question about this GGUF

1

#18 opened 2 months ago by

alexloops

the trade off is not good (new update)

👍 1

4

#28 opened 2 months ago by

rosspanda0

Qwen3.6-27b-1M上下文需求。

2

#35 opened 2 months ago by

kelei999999

IQ3XXS giving garbage output

2

#33 opened 2 months ago by

mbhagya

presence-penalty

5

#8 opened 2 months ago by

owao

random chinese characters issue with unsloth GGUF for Qwen3.6-27B for the pre and post MTP

4

#36 opened about 2 months ago by

Malmuk1

Don't forget to add MLX too, please! ;-)

1

#4 opened 2 months ago by

egodoyca

These shoudl work on ik_llama.cpp too

🚀👍 9

#3 opened 2 months ago by

ubergarm

Stable MTP first release!

❤️ 15

11

#6 opened 2 months ago by

danielhanchen

is it work for gemma4?

🤗 1

1

#9 opened 2 months ago by

koyukira

Noticeable Performance Decrease

👍 3

4

#23 opened 2 months ago by

WebWeaverWraith

New activity in unsloth/gemma-4-12b-it-GGUF about 2 months ago

Context length is at 131k instead of 256k

5

#8 opened about 2 months ago by

Orangeswim