hugypufy

hugypufy's activity

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

New activity in z-lab/Qwen3.8-27B-PARO 9 days ago

benchmarks and quality ?

#2 opened 9 days ago by

hugypufy

New activity in mudler/Qwen3.8-Flash-Next-APEX-GGUF 13 days ago

non gguf variant for vllm

#3 opened 13 days ago by

hugypufy

New activity in inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4 22 days ago

UPDATE 30/08/26

😎 1

3

#2 opened 22 days ago by

inferencerlabs

New activity in inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4 25 days ago

Q3 for 128GB bros

1

#1 opened 25 days ago by

hugypufy

New activity in amd/Qwen3.8-27B-Quark-AWQ-INT4-W4A16 26 days ago

Request Quark-AWQ-INT4-W4A8 variant

👍 5

2

#3 opened 26 days ago by

hugypufy

New activity in ChengyiX/Qwen3.8-27B-DFlash2-LocalFlash-M4Max 27 days ago

thanks ! question on prefill

1

#1 opened 27 days ago by

hugypufy

New activity in droplychee/droplychee-1.0-27b about 2 months ago

FP8 quantisation ?

2

#1 opened about 2 months ago by

hugypufy

New activity in fcobos/Qwen3.6-35B-A3B-oQ3-mtp 5 months ago

oq4 oq6 and oq8 as well ?

#1 opened 5 months ago by

hugypufy

New activity in noctrex/Qwen3.6-35B-A3B-MXFP4_MOE-GGUF 5 months ago

alternative mxfp4 with mixed shared experts and non-experts

7

#1 opened 5 months ago by

hugypufy

New activity in michaelw9999/Qwen3.5-4B-MXFP6-GGUF 5 months ago

quantisation procedure request

1

#1 opened 5 months ago by

hugypufy

New activity in mlx-community/DeepSeek-V4-Flash-2bit-DQ 5 months ago

KeyError: 'deepseek_v4'

8

#1 opened 5 months ago by

lefromage

New activity in nightmedia/Qwen3.6-35B-A3B-qx86-hi-mlx 5 months ago

!!! fastest q8 model !!!

❤️🔥 1

1

#1 opened 5 months ago by

hugypufy

New activity in pahajokiconsulting/Qwen3.6-35B-A3B-MXFP4 5 months ago

gguf ?

#1 opened 5 months ago by

hugypufy

New activity in baa-ai/MiniMax-M2.7-RAM-100GB-MLX 5 months ago

tyvm !

6

#2 opened 5 months ago by

hugypufy

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

Can i use this draft model with Q4 , Q6 and Q8 27B Models ?

👍 5

#6 opened 5 months ago by

hugypufy

New activity in baa-ai/Qwen3.5-122B-A10B-RAM-48GB-MLX 6 months ago

Request higher quants

6

#2 opened 6 months ago by

hugypufy

Request higher quants

6

#2 opened 6 months ago by

hugypufy