Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
69.7
TFLOPS
4
7
Gabriel Devenyi
gdevenyi
Follow
webxos's profile picture
1 follower
ยท
21 following
gdevenyi
AI & ML interests
None yet
Recent Activity
new
activity
2 days ago
froggeric/Qwen3.6-27B-MTP-GGUF:
--no-mmproj-offload to avoid VRAM usage
new
activity
3 days ago
YTan2000/Qwen3.6-27B-TQ3_4S:
llama.cpp-tq3 crashes loading model in "model router" mode, works fine when run with llama-server directly.
liked
a model
5 days ago
mudler/gemma-4-26B-A4B-it-APEX-GGUF
View all activity
Organizations
gdevenyi
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
New activity in
froggeric/Qwen3.6-27B-MTP-GGUF
2 days ago
--no-mmproj-offload to avoid VRAM usage
๐ค
1
2
#3 opened 3 days ago by
gdevenyi
New activity in
YTan2000/Qwen3.6-27B-TQ3_4S
3 days ago
llama.cpp-tq3 crashes loading model in "model router" mode, works fine when run with llama-server directly.
#3 opened 3 days ago by
gdevenyi
New activity in
YTan2000/Qwopus3.5-27B-v3-Abliterated-TQ3_4S
15 days ago
VRAM usage, quantization & Context length
9
#1 opened 16 days ago by
cnsiva
New activity in
mudler/Qwen3.6-35B-A3B-APEX-GGUF
20 days ago
Benchmarking visualization -- suggestion log scale for y-axis
๐
1
#5 opened 20 days ago by
gdevenyi