Baidu · First MLX build 2 Jul 2025
ERNIE-4.5-0.3B-PT
MLX
Text apache-2.0
A 361M parameter text generation model from Baidu, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 361M From Hugging Face
- Quantisation
- bf16 ERNIE-4.5-0.3B-PT-bf16-ft
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 721 MB Weights, estimated
- Downloads
- 87 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at bf16
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/ERNIE-4.5-0.3B-PT-bf16-ft --prompt "Hello"MLX builds
4 on mlx-community| ERNIE-4.5-0.3B-PT-4bit | 4-bit | 203 MB | 3 GB | 55 |
|---|---|---|---|---|
| ERNIE-4.5-0.3B-PT-4bit-ft | 4-bit | 203 MB | 3 GB | 27 |
| ERNIE-4.5-0.3B-PT-bf16-ft | bf16 | 721 MB | 3 GB | 87 |
| ERNIE-4.5-0.3B-PT-bf16 | bf16 | 721 MB | 3 GB | 31 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.