Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
78.8
TFLOPS
Wasif Basharat
wasifb
10
1
33
Follow
CrytoBoy17's profile picture
travnewmatic's profile picture
sudeposutemizligi's profile picture
4 followers
·
28 following
AI & ML interests
None yet
Recent Activity
new
activity
4 days ago
Avuja/Qwen3.8-27B-int4-AutoRound:
FYI: built-in MTP drafter acceptance permanently collapses under sustained vLLM speculative decoding
liked
a model
10 days ago
dots-studio/dots3-note-prev
liked
a model
12 days ago
peculiar-ragdoll/Qwen-Sharp-Chat-Templates
View all activity
Organizations
None yet
wasifb
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
New activity in
Avuja/Qwen3.8-27B-int4-AutoRound
4 days ago
FYI: built-in MTP drafter acceptance permanently collapses under sustained vLLM speculative decoding
1
#1 opened 4 days ago by
wasifb
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
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
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
New activity in
kai-os/Carnice-V2-27b
4 months ago
Tool-call format incompatible with vLLM on Ampere (RTX 3090) — inconsistent XML output
1
#4 opened 4 months ago by
wasifb
New activity in
Lorbus/Qwen3.6-27B-int4-AutoRound
4 months ago
Heads-up for Ampere users: tq-t4nc recipe + MTP doesn't work with CUDA graphs
3
#2 opened 4 months ago by
wasifb
New activity in
RedHatAI/gemma-4-31B-it-speculator.dflash
4 months ago
Ampere (sm_86) compatibility findings — two-path blocker on 2× RTX 3090
❤️
1
#1 opened 4 months ago by
wasifb
New activity in
Intel/gemma-4-31B-it-int4-AutoRound
4 months ago
Fails to load on Ampere (sm_86) at TP=2: Marlin kernel rejects 32-dim weight slice
2
#3 opened 4 months ago by
wasifb
Fails to load on Ampere (sm_86) at TP=2: Marlin kernel rejects 32-dim weight slice
2
#3 opened 4 months ago by
wasifb