Hugging Face
Search models, datasets, users...
Ctrl K
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
doth4580
/
Qwen3.8-Flash-Next-FP4-Local
Like
0
Image-Text-to-Text
Safetensors
qwen4_exp
nvidia
ModelOpt
Qwen3.8
quantized
FP4
NVFP4
MXFP8
Mixture of Experts
vision
mtp
speculative-decoding
exl3
dgx-spark
veloGB10
conversational
8-bit precision
modelopt
License:
nvidia-open-model-agreement
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
Qwen3.8-Flash-Next-FP4-Local
Commit History
Nov 10
5 days ago
06:21
Add files using upload-large-folder tool
doth4580
Verified signature
ab97eac
Nov 9
6 days ago
17:24
Model card: sources and credits, veloGB10 TP=1/2/4 instructions, measured numbers, IP note, original card
doth4580
Verified signature
7fd8cd6
17:10
initial commit
doth4580
Verified signature
10dd6c8
