William Pieh

WTPieh's activity

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

liked a model 20 days ago

Qwen/Qwen3.8-Flash-Next

Image-Text-to-Text • 180B • Updated Aug 27 • 1.87M • • 6.1k

liked a model about 1 month ago

gorbatjovy/qwen3.8-flash-next-abliterated-NVFP4-plefp8

Image-Text-to-Text • 117B • Updated Aug 27 • 485 • 3

updated a model about 1 month ago

PiehSoft/Qwen3.8-Flash-Next-Abliterated-NVFP4-FP8PBWO

Text Generation • 120B • Updated Sep 7 • 220 • 1

published a model about 1 month ago

PiehSoft/Qwen3.8-Flash-Next-Abliterated-NVFP4-FP8PBWO

Text Generation • 120B • Updated Sep 7 • 220 • 1

liked a model about 2 months ago

gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090

Image-Text-to-Text • 15B • Updated Sep 10 • 399k • 173

New activity in PiehSoft/Qwen3.6-40B-Deckard-MTP 3 months ago

I can't get it to load with llama.cpp

6

#5 opened 3 months ago by

sa13ma

Q8 quant

2

#4 opened 3 months ago by

chrisburri

New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF 4 months ago

I am getting very good results with this model but its a bit slow, any chance for MTP?

34

#17 opened 4 months ago by

bissli

updated a model 4 months ago

PiehSoft/Qwen3.6-40B-Deckard-MTP

Text Generation • 39B • Updated Jun 18 • 256 • 23

New activity in PiehSoft/Qwen3.6-40B-Deckard-MTP 4 months ago

Single-needle retrieval holds to 1M tokens (3.85x YaRN) + the llama.cpp context-cap workaround.

🚀 2

1

#3 opened 4 months ago by

WTPieh

Strix Halo gfx1151 ROCmFP4 support

7

#2 opened 4 months ago by

BebopVox

not new and first

🤯 1

1

#1 opened 4 months ago by

Black6spdZ

liked a model 4 months ago

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated Jun 12 • 272k • 3.11k

New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking 5 months ago

MTP should be left in place, its trivial to add back in and it is beneficial.

👍👀 3

12

#4 opened 5 months ago by

tcclaviger

New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF 5 months ago

Cannot use MTP

5

#6 opened 5 months ago by

nickmok

published a model 5 months ago

PiehSoft/Qwen3.6-40B-Deckard-MTP

Text Generation • 39B • Updated Jun 18 • 256 • 23

updated a model 5 months ago

PiehSoft/Qwopus3.6-27B-Abliterated-MTP-GGUF

27B • Updated May 25 • 90 • 9

liked a model 5 months ago

PiehSoft/Qwopus3.6-27B-Abliterated-MTP-GGUF

27B • Updated May 25 • 90 • 9

published a model 5 months ago

PiehSoft/Qwopus3.6-27B-Abliterated-MTP-GGUF

27B • Updated May 25 • 90 • 9

updated a model 5 months ago

PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4

Text Generation • 41B • Updated May 9 • 101