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
BasinShapers
/
flux2-klein-4b-webgpu
Like
0
Follow
The Basin Maintenance Division
1
Text-to-Image
kaminos
webgpu
flux
quantized
browser
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
flux2-klein-4b-webgpu
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
lyonsno
Model card: about 14 s per 512 image on a 16 GB M2 Pro
5c4f0f7
verified
3 days ago
dit-q2
Jank levels: 3-bit (dit-q3) and 2-bit (dit-q2) transformers
5 days ago
dit-q3
Jank levels: 3-bit (dit-q3) and 2-bit (dit-q2) transformers
5 days ago
dit
Lean int4 weights: group 128, int4 globals; 3.2 GB page download
6 days ago
te
Lean int4 weights: group 128, int4 globals; 3.2 GB page download
6 days ago
vae
Add gzip copies of the bundles and tokenizer (9% smaller page download)
6 days ago
.gitattributes
Safe
1.57 kB
FLUX.2 [klein] 4B packed for WebGPU (int4)
6 days ago
LICENSE
Safe
9.58 kB
FLUX.2 [klein] 4B packed for WebGPU (int4)
6 days ago
README.md
3.35 kB
Model card: about 14 s per 512 image on a 16 GB M2 Pro
3 days ago
