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
DevelopingDad
/
Qwen3.8-Flash-Next-FP4-Local-Abliterated
Like
1
Image-Text-to-Text
Safetensors
mlabonne/harmful_behaviors
mlabonne/harmless_alpaca
qwen4_exp
qwen3.8
qwen3.8-flash-next
abliterated
heretic
nvfp4
mxfp8
modelopt
mtp
dgx-spark
vllm
conversational
8-bit precision
arxiv:
2406.11717
License:
nvidia-open-model-agreement
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Qwen3.8-Flash-Next-FP4-Local-Abliterated
/
reencode
21.9 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
DevelopingDad
MXFP8 re-encode of the attention output projections
51f2415
verified
3 days ago
mxfp8_reencode.py
Safe
8.83 kB
MXFP8 re-encode of the attention output projections
3 days ago
reencode-report.json
Safe
13 kB
MXFP8 re-encode of the attention output projections
3 days ago
