MLX Community · First MLX build 21 Mar 2024
llama2-70b-qnt4bit
MLX
Text
A 69B parameter text generation model, with one MLX build.
- Parameters
- 69B From Hugging Face
- Quantisation
- Unstated llama2-70b-qnt4bit
- Memory needed
- 310 GB Estimate, unified memory
- Download
- 275 GB Weights, estimated
- Downloads
- 37 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 310 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/llama2-70b-qnt4bit --prompt "Hello"MLX builds
1 on mlx-community| llama2-70b-qnt4bit | Unstated | 275 GB | 310 GB | 37 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.