William Pieh

WTPieh's activity

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

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

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

28

#17 opened 11 days ago by

bissli

updated a model 7 days ago

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

Text Generation • 39B • Updated 6 days ago • 2.66k • 11

New activity in PiehSoft/Qwen3.6-40B-Deckard-MTP 7 days ago

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

🚀 1

1

#3 opened 7 days ago by

WTPieh

New activity in PiehSoft/Qwen3.6-40B-Deckard-MTP 9 days ago

Strix Halo gfx1151 ROCmFP4 support

7

#2 opened 14 days ago by

BebopVox

New activity in PiehSoft/Qwen3.6-40B-Deckard-MTP 14 days ago

not new and first

🤯 1

1

#1 opened 15 days ago by

Black6spdZ

liked a model 24 days ago

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated 13 days ago • 408k • 2.35k

New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking 28 days ago

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

👍👀 3

12

#4 opened about 2 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 28 days ago

Cannot use MTP

5

#6 opened about 1 month ago by

nickmok

published a model 28 days ago

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

Text Generation • 39B • Updated 6 days ago • 2.66k • 11

updated a model about 1 month ago

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

27B • Updated May 25 • 1.09k • 8

liked a model about 1 month ago

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

27B • Updated May 25 • 1.09k • 8

published a model about 1 month ago

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

27B • Updated May 25 • 1.09k • 8

updated a model about 2 months ago

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

Text Generation • 41B • Updated May 9 • 262

published a model about 2 months ago

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

Text Generation • 41B • Updated May 9 • 262

updated a model about 2 months ago

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

Text Generation • 71B • Updated May 9 • 290

published a model about 2 months ago

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

Text Generation • 71B • Updated May 9 • 290