Hugging Face
Models
Datasets
Spaces
Buckets
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
EliovpAI
/
Qwen3.8-27B-W3Rot-INT3-Paiton-RDNA4
Like
5
Follow
Eliovp
10
Text Generation
paiton
vllm
amd
rocm
rdna4
gfx1201
int3
3-bit
gptq
hadamard
w3a4
dflash2
speculative-decoding
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Copy to bucket
New discussion
New pull request
Resources
PR & discussions documentation
Code of Conduct
Hub documentation
All
Discussions
Pull requests
View closed (0)
Sort: Recently created
Performance is great! However I see random "torch.OutOfMemoryError: CUDA out of memory." errors, during kv allocation.
5
#1 opened 23 days ago by
Andy4OS
