DeepSeek-V4-Flash-VQ-3.2bpw
3.2B open-weight LLM by TheDrainFlorist
Live
Open / InstallLast updated October 23, 2026
Description
DeepSeek-V4-Flash-VQ-3.2bpw is an open-weight text-generation model with roughly 3.2B parameters published by TheDrainFlorist on the Hugging Face Hub. It has 821 downloads. Runs with mlx.
Community Metrics
Views
0
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
TheDrainFlorist
Platform
api
Pricing model
free
Categories
- Productivity
Tags
- deepseek_v4
- quantized
- vector-quantization
- apple-silicon
- deepseek
- text-generation
- conversational
- en
Capabilities
- Text generation
- Conversational
- Library: mlx
- 3.2B parameters
Information
TypeLarge Language Model
Model TypeText Generation
SourceHuggingface Models
AddedOctober 4, 2026