Instructions to use mlx-community/SmolLM3-3B-Base-5bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/SmolLM3-3B-Base-5bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mlx-community/SmolLM3-3B-Base-5bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Transformers.js
How to use mlx-community/SmolLM3-3B-Base-5bit with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'mlx-community/SmolLM3-3B-Base-5bit'); - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use mlx-community/SmolLM3-3B-Base-5bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "mlx-community/SmolLM3-3B-Base-5bit" --prompt "Once upon a time"
- Atomic Chat
Download special_tokens_map.json from mlx-community/SmolLM3-3B-Base-5bit: direct link, hf CLI and curl.
- Browser
- Download file 151 Bytes
-
https://huggingface.co/mlx-community/SmolLM3-3B-Base-5bit/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://mlx-community/SmolLM3-3B-Base-5bit/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/mlx-community/SmolLM3-3B-Base-5bit/resolve/main/special_tokens_map.json
151 Bytes
| { | |
| "eos_token": { | |
| "content": "<|end_of_text|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |