Baichuan-M1-14B-Instruct-4bit-ft
mlx-community/Baichuan-M1-14B-Instruct-4bit-ft
Text generation · mlx
4-bit Open on Hugging Face
Parameters
14B
Weights (est.)
≈ 8.1 GB
Mac memory (est.)
16 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/Baichuan-M1-14B-Instruct-4bit-ft --prompt "Hello"
Details
- Base model
- baichuan-inc/Baichuan-M1-14B-Instruct (quantized)
- Vendor
- baichuan-inc
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 81 in the last 30 days · 684 all time · 0 likes
- Published
- 2025-07-13 · updated 2025-07-13 (1y ago)
- Languages
- en, zh
- Tags
- baichuan_m1, medical, custom_code
Other MLX builds of baichuan-inc/Baichuan-M1-14B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Baichuan-M1-14B-Instruct-4bit | 4-bit | ≈ 8.1 GB | 16 GB+ | 90 |
| Baichuan-M1-14B-Instruct-4bit-ft (this one) | 4-bit | ≈ 8.1 GB | 16 GB+ | 81 |
| Baichuan-M1-14B-Instruct-8bit | 8-bit | ≈ 15.4 GB | 24 GB+ | 36 |
| Baichuan-M1-14B-Instruct | — | ≈ 28.9 GB | 48 GB+ | 58 |