4-bit Open on Hugging Face
Parameters
1.8B
Weights (est.)
≈ 1.0 GB
Mac memory (est.)
8 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.
Details
- Base model
- Tencent-Hunyuan/Hy-MT2-1.8B
- Vendor
- Tencent-Hunyuan
- Task
- Translation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 1.3K in the last 30 days · 7.3K all time · 5 likes
- Published
- 2026-05-26 · updated 2026-05-30 (5mo ago)
- Languages
- multilingual
- Tags
- hunyuan_v1_dense, apple-silicon, mlx-lm
Other MLX builds of Tencent-Hunyuan/Hy-MT2-1.8B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Hy-MT2-1.8B-4bit (this one) | 4-bit | ≈ 1.0 GB | 8 GB+ | 1.3K |
| Hy-MT2-1.8B-8bit | 8-bit | ≈ 1.9 GB | 8 GB+ | 368 |
| Hy-MT2-1.8B | — | ≈ 3.6 GB | 8 GB+ | 166 |
| Hy-MT2-1.8B-bf16 | bf16 | ≈ 3.6 GB | 8 GB+ | 57 |