MLX Community · First MLX build 27 Jun 2024
gemma-2-9b-it
MLX
Text gemma
A 9.2B parameter text generation model, with 3 MLX builds, from 4-bit to fp16.
- Parameters
- 9.2B From Hugging Face
- Quantisation
- 4-bit gemma-2-9b-it-4bit
- Memory needed
- 8 GB Estimate, unified memory
- Download
- 5.2 GB Weights, estimated
- Downloads
- 18K 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 8 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/gemma-2-9b-it-4bit --prompt "Hello"MLX builds
3 on mlx-community| gemma-2-9b-it-4bit | 4-bit | 5.2 GB | 8 GB | 18K |
|---|---|---|---|---|
| gemma-2-9b-it-8bit | 8-bit | 9.8 GB | 13 GB | 153 |
| gemma-2-9b-it-fp16 | fp16 | 18.5 GB | 23 GB | 124 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.