Hugging Face · First MLX build 8 Jul 2025
SmolLM3-3B
MLX
Text apache-2.0 Trending
A 3.1B parameter text generation model from Hugging Face, with 9 MLX builds, from 3-bit to bf16.
- Parameters
- 3.1B From Hugging Face
- Quantisation
- 4-bit SmolLM3-3B-4bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.7 GB Weights, estimated
- Downloads
- 3.6K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 9 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at 4-bit
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/SmolLM3-3B-4bit --prompt "Hello"MLX builds
9 on mlx-community| SmolLM3-3B-3bit | 3-bit | 1.3 GB | 4 GB | 60 |
|---|---|---|---|---|
| SmolLM3-3B-4bit | 4-bit | 1.7 GB | 4 GB | 3.6K |
| SmolLM3-3B-4bit-DWQ | 4-bit DWQ | 1.7 GB | 4 GB | 73 |
| SmolLM3-3B-5bit | 5-bit | 2.1 GB | 5 GB | 47 |
| SmolLM3-3B-6bit | 6-bit | 2.5 GB | 5 GB | 37 |
| SmolLM3-3B-8bit | 8-bit | 3.3 GB | 6 GB | 133 |
| SmolLM3-3B-bf16 | bf16 | 6.2 GB | 9 GB | 62 |
| SmolLM3-3B-abliterated-bf16 | bf16 | 6.2 GB | 9 GB | 54 |
| SmolLM3-3B-gabliterated-bf16 | bf16 | 6.2 GB | 9 GB | 30 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.