Qwen3.6-26B-A3B-KREAP-8bit-MLX
26B open-weight LLM by RAS-LAB
Live
Open / InstallLast updated October 23, 2026
Description
Qwen3.6-26B-A3B-KREAP-8bit-MLX is an open-weight text-generation model with roughly 26B parameters published by RAS-LAB on the Hugging Face Hub. It has 1,234 downloads. Runs with mlx.
Community Metrics
Views
0
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
RAS-LAB
Platform
api
Pricing model
free
Categories
- Productivity
Tags
- qwen3_5_moe
- qwen3.6
- mixture-of-experts
- reap
- expert-pruning
- korean
- 8-bit
- text-generation
Capabilities
- Text generation
- Conversational
- Library: mlx
- 26B parameters
Information
TypeLarge Language Model
Model TypeText Generation
SourceHuggingface Models
AddedOctober 4, 2026