Wasif Basharat

wasifb's activity

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

New activity in migtissera/Tess-4-27B 11 days ago

How does it compare to Ornith

3

#11 opened 12 days ago by

TESTPOINTrxz

New activity in migtissera/Tess-4-27B-NVFP4 12 days ago

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

#2 opened 12 days ago by

wasifb

New activity in huginnfork/Tess-4-27B-NVFP4A16 13 days ago

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

#1 opened 13 days ago by

wasifb

New activity in migtissera/Tess-4-27B-EAGLE3 13 days ago

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

#1 opened 13 days ago by

wasifb

New activity in yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF about 1 month ago

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

🚀👍 9

1

#9 opened about 1 month ago by

wasifb

New activity in kai-os/Carnice-V2-27b 3 months ago

Tool-call format incompatible with vLLM on Ampere (RTX 3090) — inconsistent XML output

1

#4 opened 3 months ago by

wasifb

New activity in Lorbus/Qwen3.6-27B-int4-AutoRound 3 months ago

Heads-up for Ampere users: tq-t4nc recipe + MTP doesn't work with CUDA graphs

3

#2 opened 3 months ago by

wasifb

New activity in RedHatAI/gemma-4-31B-it-speculator.dflash 3 months ago

Ampere (sm_86) compatibility findings — two-path blocker on 2× RTX 3090

❤️ 1

#1 opened 3 months ago by

wasifb

New activity in Intel/gemma-4-31B-it-int4-AutoRound 3 months ago

Fails to load on Ampere (sm_86) at TP=2: Marlin kernel rejects 32-dim weight slice

2

#3 opened 3 months ago by

wasifb

Fails to load on Ampere (sm_86) at TP=2: Marlin kernel rejects 32-dim weight slice

2

#3 opened 3 months ago by

wasifb