Qwen3.6-35B-A3B-MTPLX-Speed-BF16-MTP
35B open-weight LLM by Joonix71
Live
Open / InstallLast updated October 23, 2026
Description
Qwen3.6-35B-A3B-MTPLX-Speed-BF16-MTP is an open-weight text-generation model with roughly 35B parameters published by Joonix71 on the Hugging Face Hub. It has 392 downloads. Runs with mlx.
Community Metrics
Views
0
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
Joonix71
Platform
api
Pricing model
free
Categories
- Coding
- Productivity
Tags
- qwen3_5_moe
- mtplx
- speculative-decoding
- mtp
- qwen3.6
- text-generation
- conversational
- 4-bit
Capabilities
- Text generation
- Conversational
- Library: mlx
- 35B parameters
Information
TypeLarge Language Model
Model TypeText Generation
SourceHuggingface Models
AddedOctober 15, 2026