Qwen3.8-Flash-Next-DERISKED-MTPLX-Optimized-Speed
Open-weight LLM by p0ly31
Live
Open / InstallLast updated October 23, 2026
Description
Qwen3.8-Flash-Next-DERISKED-MTPLX-Optimized-Speed is an open-weight text-generation model published by p0ly31 on the Hugging Face Hub. It has 746 downloads. Runs with mlx.
Community Metrics
Views
6
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
p0ly31
Platform
api
Pricing model
free
Categories
- Coding
- Productivity
Tags
- qwen4_exp
- apple-silicon
- macos
- speculative-decoding
- multi-token-prediction
- qwen
- qwen3.8-flash-next
- moe
Capabilities
- Text generation
- Conversational
- Library: mlx
Information
TypeLarge Language Model
Model TypeText Generation
SourceHuggingface Models
AddedSeptember 27, 2026