MLX Community · First MLX build 15 Jul 2025
Qwen3-1.7B-dwq-3bit-gs128
MLX
mit
A model, with one MLX build at 3-bit DWQ.
- Parameters
- — Not published
- Quantisation
- 3-bit DWQ Qwen3-1.7B-dwq-3bit-gs128
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 14 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Qwen3-1.7B-dwq-3bit-gs128MLX builds
1 on mlx-community| Qwen3-1.7B-dwq-3bit-gs128 | 3-bit DWQ | — | — | 14 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.