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
vessl
/
Kimi-K3-W4AFP8
Like
12
Follow
VESSL AI
31
Image-Text-to-Text
Safetensors
English
Chinese
sglang
kimi_k3
kimi
kimi-k3
Mixture of Experts
mixture-of-experts
w4afp8
int4
fp8
quantized
custom_code
8-bit precision
License:
kimi-k3
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Kimi-K3-W4AFP8
/
apply_patch.py
Commit History
Aug 6
04:54
Attention projections (q/k/v/g/o) to FP8 E4M3 per-tensor; add apply_patch.py
lucasnam
Verified signature
376ac49
