MLX Community · First MLX build 6 Apr 2025
Llama-4-Maverick-17B-16E-Instruct
MLX
Text llama4
A 401B parameter text generation model, with 2 MLX builds, from 4-bit to 6-bit.
- Parameters
- 401B From Hugging Face
- Quantisation
- 4-bit Llama-4-Maverick-17B-16E-Instruct-4bit
- Memory needed
- 254 GB Estimate, unified memory
- Download
- 225 GB Weights, estimated
- Downloads
- 168 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 254 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-4-Maverick-17B-16E-Instruct-4bit --prompt "Hello"MLX builds
2 on mlx-community| Llama-4-Maverick-17B-16E-Instruct-4bit | 4-bit | 225 GB | 254 GB | 168 |
|---|---|---|---|---|
| Llama-4-Maverick-17B-16E-Instruct-6bit | 6-bit | 326 GB | 366 GB | 62 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.