MLX Community · First MLX build 25 Sept 2024
Llama-3.2-3B-Instruct
MLX
Text llama3.2
A 3.2B parameter text generation model, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 3.2B From Hugging Face
- Quantisation
- 4-bit Llama-3.2-3B-Instruct-4bit
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 1.8 GB Weights, estimated
- Downloads
- 22K 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 5 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/Llama-3.2-3B-Instruct-4bit --prompt "Hello"MLX builds
3 on mlx-community| Llama-3.2-3B-Instruct-4bit | 4-bit | 1.8 GB | 5 GB | 22K |
|---|---|---|---|---|
| Llama-3.2-3B-Instruct-8bit | 8-bit | 3.4 GB | 6 GB | 3.0K |
| Llama-3.2-3B-Instruct-bf16 | bf16 | 6.4 GB | 10 GB | 1.5K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.