Hy3-preview-MTP-4bit
mlx-community/Hy3-preview-MTP-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
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.
Details
- Base model
- tencent/Hy3-preview (finetune)
- Vendor
- tencent
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- tencent-hunyuan-community
- Downloads
- 0 in the last 30 days · 0 all time · 0 likes
- Published
- 2026-07-11 · updated 2026-07-11 (4mo ago)
- Tags
- speculative-decoding, multi-token-prediction, hunyuan
Other MLX builds of tencent/Hy3-preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Hy3-preview-4bit | 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 (this one) | 4-bit | — | — | 0 |