Meta · First MLX build 14 Oct 2026
Llama-Guard-3-1B
MLX
Text llama3.2
A 1.5B parameter text generation model from Meta, with 3 MLX builds, from 4-bit to 16-bit.
- Parameters
- 1.5B From Hugging Face
- Quantisation
- 16-bit Llama-Guard-3-1B-chat-mlx-16bit
- Memory needed
- 6 GB Estimate, unified memory
- Download
- 3.0 GB Weights, estimated
- Downloads
- 342 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 6 GB at 16-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/Llama-Guard-3-1B-chat-mlx-16bit --prompt "Hello"MLX builds
3 on mlx-community| Llama-Guard-3-1B-chat-mlx-4bit | 4-bit | 843 MB | 3 GB | 297 |
|---|---|---|---|---|
| Llama-Guard-3-1B-chat-mlx-8bit | 8-bit | 1.6 GB | 4 GB | 275 |
| Llama-Guard-3-1B-chat-mlx-16bit | 16-bit | 3.0 GB | 6 GB | 342 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.