4-bit Open on Hugging Face
Parameters
295B
Weights (est.)
≈ 166 GB
Mac memory (est.)
192 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Hy3-preview-4bit --prompt "Hello"
Details
- Base model
- tencent/Hy3-preview (quantized)
- Vendor
- tencent
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- other
- Downloads
- 74 in the last 30 days · 3.3K all time · 4 likes
- Published
- 2026-04-27 · updated 2026-04-27 (6mo ago)
- Tags
- hy_v3
Other MLX builds of tencent/Hy3-preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Hy3-preview-4bit (this one) | 4-bit | ≈ 166 GB | 192 GB+ | 74 |
| Hy3-preview-6bit | 6-bit | ≈ 240 GB | 512 GB+ | 34 |
| Hy3-preview-8bit | 8-bit | ≈ 313 GB | 512 GB+ | 27 |
| Hy3-preview-MTP-4bit | 4-bit | — | — | 0 |