Wasif Basharat

wasifb's activity

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

New activity in Avuja/Qwen3.8-27B-int4-AutoRound 5 days ago

FYI: built-in MTP drafter acceptance permanently collapses under sustained vLLM speculative decoding

2

#1 opened 5 days ago by

wasifb

liked a model 11 days ago

dots-studio/dots3-note-prev

Image-Text-to-Text • 288B • Updated 10 days ago • 1.81k • 262

liked a model 13 days ago

peculiar-ragdoll/Qwen-Sharp-Chat-Templates

Updated about 9 hours ago • 234

liked a model 27 days ago

rdtand/Qwen3.6-27B-PrismaAURA-5.5bit-vllm

20B • Updated Jun 25 • 43.7k • 29

liked a model about 1 month ago

Nanbeige/Nanbeige4.2-3B

Text Generation • 4B • Updated about 4 hours ago • 58.1k • 712

updated a model about 1 month ago

wasifb/Tess-4-27B-AutoRound-W4A16-club3090

3B • Updated Jul 20 • 118

published a model about 1 month ago

wasifb/Tess-4-27B-AutoRound-W4A16-club3090

3B • Updated Jul 20 • 118

New activity in migtissera/Tess-4-27B about 1 month ago

How does it compare to Ornith

3

#11 opened about 1 month ago by

TESTPOINTrxz

liked a model about 1 month ago

YourHighnessLA/Tess-4-27B-EAGLE3-GGUF

0.6B • Updated Jul 11 • 34 • 2

New activity in migtissera/Tess-4-27B-NVFP4 about 1 month ago

Fix chat_template.jinja — developer-role support + tool-argument mapping (stock template crashes agentic harnesses)

#2 opened about 1 month ago by

wasifb

New activity in huginnfork/Tess-4-27B-NVFP4A16 about 1 month ago

Counter-datapoint: the inherited MTP head gets 0.62 accept / +38% via llama.cpp external draft-mtp (vLLM-useless != useless)

#1 opened about 1 month ago by

wasifb

New activity in migtissera/Tess-4-27B-EAGLE3 about 1 month ago

2x RTX 3090 measurements: net-negative vs quantized trunks (~40% acceptance) — tap/quant/template forensics

#1 opened about 1 month ago by

wasifb

liked a model about 2 months ago

migtissera/Tess-4-27B

Image-Text-to-Text • 28B • Updated Jul 10 • 214 • 143

liked 6 models 2 months ago

ornith-ai/Ornith-1.0-9B-GGUF

Text Generation • 9B • Updated Jun 25 • 4.95M • 658

nvidia/personaplex-7b-v1

Audio-to-Audio • 8B • Updated Mar 2 • 168k • • 2.68k

kaitchup/Qwen3.6-27B-GGUF-MoQ

27B • Updated Jun 16 • 4.44k • 21

bytkim/Qwen3.6-27B-MTP-pi-reasoning-GGUF

Image-Text-to-Text • 27B • Updated Jun 20 • 1.37k • 59

prithivMLmods/VibeThinker-3B-GGUF

Text Generation • 3B • Updated Jun 16 • 4.79k • 73

WeiboAI/VibeThinker-3B

Text Generation • 3B • Updated Jun 30 • 139k • • 832

New activity in yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF 2 months ago

Quality eval on a single RTX 3090 — strong instruct/code-quality, soft tool-calling

🔥👍 9

1

#9 opened 2 months ago by

wasifb