Qwen3-Coder-16B-A3B-KREAP-MLX
16B open-weight LLM by RAS-LAB
Live
Open / InstallLast updated October 23, 2026
Description
Qwen3-Coder-16B-A3B-KREAP-MLX is an open-weight text-generation model with roughly 16B parameters published by RAS-LAB on the Hugging Face Hub. It has 1,251 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
- Coding
- Productivity
Tags
- qwen3_moe
- moe
- pruning
- reap
- k-reap
- korean
- expert-pruning
- text-generation
Capabilities
- Text generation
- Conversational
- Library: mlx
- 16B parameters
Information
TypeLarge Language Model
Model TypeText Generation
SourceHuggingface Models
AddedSeptember 29, 2026