4-bit Open on Hugging Face
Parameters
361M
Weights (est.)
≈ 203 MB
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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/ERNIE-4.5-0.3B-PT-4bit --prompt "Hello"
Details
- Base model
- baidu/ERNIE-4.5-0.3B-PT (quantized)
- Vendor
- baidu
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 56 in the last 30 days · 830 all time · 1 likes
- Published
- 2025-07-02 · updated 2025-07-02 (1y ago)
- Languages
- en, zh
- Tags
- ernie4_5, ERNIE4.5, custom_code
Other MLX builds of baidu/ERNIE-4.5-0.3B-PT
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| ERNIE-4.5-0.3B-PT-4bit (this one) | 4-bit | ≈ 203 MB | 8 GB+ | 56 |
| ERNIE-4.5-0.3B-PT-4bit-ft | 4-bit | ≈ 203 MB | 8 GB+ | 27 |
| ERNIE-4.5-0.3B-PT-bf16-ft | bf16 | ≈ 721 MB | 8 GB+ | 91 |
| ERNIE-4.5-0.3B-PT-bf16 | bf16 | ≈ 721 MB | 8 GB+ | 30 |