Instructions to use mlx-community/SmolLM3-3B-Base-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/SmolLM3-3B-Base-6bit 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-6bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Transformers.js
How to use mlx-community/SmolLM3-3B-Base-6bit 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-6bit'); - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use mlx-community/SmolLM3-3B-Base-6bit 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-6bit" --prompt "Once upon a time"
- Atomic Chat
|
Download README.md from mlx-community/SmolLM3-3B-Base-6bit: direct link, hf CLI and curl.
- Browser
- Download file 932 Bytes
-
https://huggingface.co/mlx-community/SmolLM3-3B-Base-6bit/resolve/main/README.md
- Command line
-
hf download hf://mlx-community/SmolLM3-3B-Base-6bit/README.md
-
curl -L -o README.md https://huggingface.co/mlx-community/SmolLM3-3B-Base-6bit/resolve/main/README.md
932 Bytes
metadata
library_name: mlx
license: apache-2.0
language:
- en
- fr
- es
- it
- pt
- zh
- ar
- ru
tags:
- transformers.js
- mlx
base_model: HuggingFaceTB/SmolLM3-3B-Base
pipeline_tag: text-generation
mlx-community/SmolLM3-3B-Base-6bit
This model mlx-community/SmolLM3-3B-Base-6bit was converted to MLX format from HuggingFaceTB/SmolLM3-3B-Base using mlx-lm version 0.25.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/SmolLM3-3B-Base-6bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)