MLX Community · First MLX build 23 May 2025
Llama-3.3-70B-Instruct
MLX
Text llama3.3
A 71B parameter text generation model, with one MLX build at 4-bit DWQ.
- Parameters
- 71B From Hugging Face
- Quantisation
- 4-bit DWQ Llama-3.3-70B-Instruct-4bit-DWQ
- Memory needed
- 47 GB Estimate, unified memory
- Download
- 39.7 GB Weights, estimated
- Downloads
- 262 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 47 GB at 4-bit DWQ
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-3.3-70B-Instruct-4bit-DWQ --prompt "Hello"MLX builds
1 on mlx-community| Llama-3.3-70B-Instruct-4bit-DWQ | 4-bit DWQ | 39.7 GB | 47 GB | 262 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.