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
nerkyor
/
Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-MTP-NVFP4
Like
3
Text Generation
Safetensors
English
Chinese
qwen3.8
nvfp4
mixed-precision
modelopt
sglang
mtp
multimodal
sft
simpo
efficient-thinking
int8
w8a8
qat
compressed-tensors
dynamic-quantization
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Copy to bucket
new
main
Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-MTP-NVFP4
/
assets
/
int8-w8a8-qat-quality-mtp-v2-en.png
Commit History
Sep 12
01:59
Publish reviewed INT8 W8A8 QAT native MTP3 card
nerkyor
Verified signature
bc61e36
