2-bit Open on Hugging Face
Parameters
295B
Weights (est.)
≈ 92.3 GB
Mac memory (est.)
128 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-oQ2e-2.31bpw --prompt "Hello"
Details
- Base model
- tencent/Hy3 (quantized)
- Vendor
- tencent
- Task
- Text generation
- Quantisation
- 2-bit
- Licence
- apache-2.0
- Downloads
- 78 in the last 30 days · 479 all time · 2 likes
- Published
- 2026-07-15 · updated 2026-07-15 (3mo ago)
- Tags
- hy_v3, imatrix, quantized, hunyuan, 2.31bpw
Other MLX builds of tencent/Hy3
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Hy3-OptiQ-2bit | 2-bit | ≈ 92.3 GB | 128 GB+ | 149 |
| Hy3-oQ2 | 2-bit | ≈ 92.3 GB | 128 GB+ | 82 |
| Hy3-oQ2e-2.31bpw (this one) | 2-bit | ≈ 92.3 GB | 128 GB+ | 78 |
| Hy3-oQ2e | 2-bit | ≈ 92.3 GB | 128 GB+ | 56 |
| Hy3-oQ2e-2.33bpw | 2-bit | ≈ 92.3 GB | 128 GB+ | 42 |
| Hy3-oQ2e-2.37bpw | 2-bit | ≈ 92.3 GB | 128 GB+ | 38 |