MLX Community · First MLX build 18 Apr 2024
WizardLM2-8x22B
MLX
Text
A 22B parameter text generation model, with one MLX build at 4-bit.
- Parameters
- 22B From Hugging Face
- Quantisation
- 4-bit WizardLM2-8x22B-4bit-mlx
- Memory needed
- 24 GB Estimate, unified memory
- Download
- 19.0 GB Weights, estimated
- Downloads
- 21 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 24 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/WizardLM2-8x22B-4bit-mlx --prompt "Hello"MLX builds
1 on mlx-community| WizardLM2-8x22B-4bit-mlx | 4-bit | 19.0 GB | 24 GB | 21 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.