Meta · First MLX build 2 Jan 2025
Llama-3.2-1B-Instruct
MLX
Text llama3.2
A 1.2B parameter text generation model from Meta, with 2 MLX builds.
- Parameters
- 1.2B From Hugging Face
- Quantisation
- Unstated Llama-3.2-1B-Instruct-MLXTuned
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.5 GB Weights, estimated
- Downloads
- 93 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 5 GB at Unstated
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-3.2-1B-Instruct-MLXTuned --prompt "Hello"MLX builds
2 on mlx-community| Llama-3.2-1B-Instruct-MLXTuned | Unstated | 2.5 GB | 5 GB | 93 |
|---|---|---|---|---|
| Llama-3.2-1B-Instruct-mlx-FinGreyLit-finetuned | Unstated | 2.5 GB | 5 GB | 50 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.