4-bit Open on Hugging Face
Parameters
30B
Weights (est.)
≈ 16.9 GB
Mac memory (est.)
24 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/Hy-Memory-30B-A3B-4bit --prompt "Hello"
Details
- Base model
- tencent/Hy-Memory-30B-A3B (quantized)
- Vendor
- tencent
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 360 in the last 30 days · 360 all time · 0 likes
- Published
- 2026-10-21 · updated 2026-10-21 (21d ago)
- Languages
- en, zh
- Tags
- hy_v3, memory
Other MLX builds of tencent/Hy-Memory-30B-A3B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Hy-Memory-30B-A3B-4bit (this one) | 4-bit | ≈ 16.9 GB | 24 GB+ | 360 |
| Hy-Memory-30B-A3B-8bit | 8-bit | ≈ 32.0 GB | 48 GB+ | 311 |