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
surogate
/
Qwen3.5-4B-SWQ
Like
1
Follow
Surogate
42
Image-Text-to-Text
Safetensors
qwen3_5
swq
quantization
vllm
qwen3.5
conversational
8-bit precision
surogate_slq
arxiv:
2605.02404
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
Qwen3.5-4B-SWQ
/
preprocessor_config.json
Commit History
Aug 14
07:59
SWQ 5.66 bpp multimodal: 3.3 GB, no benchmark separates it from BF16
flaviusburca
Verified signature
a17d385
