Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-4.7bpw
4.7B open-weight LLM by ddalcu
Live
Open / InstallLast updated October 28, 2026
Description
Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-4.7bpw is an open-weight text-generation model with roughly 4.7B parameters published by ddalcu on the Hugging Face Hub. It has 4,652 downloads. Runs with mlx-serve.
Community Metrics
Views
30
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
ddalcu
Platform
api
Pricing model
free
Categories
- Productivity
Tags
- mlx-serve
- qwen4_exp
- moe
- sparse-attention
- ngram-embedding
- text-generation
- conversational
- 4-bit
Capabilities
- Text generation
- Conversational
- Library: mlx-serve
- 4.7B parameters
Information
TypeLarge Language Model
Model TypeText Generation
SourceHuggingface Models
AddedOctober 28, 2026