UCLA-AGI · First MLX build 22 Jul 2025
Gemma-2-9B-It-SPPO-Iter3
MLX
Text gemma
A 9.2B parameter text generation model from UCLA-AGI, with 2 MLX builds, from 6-bit to 8-bit.
- Parameters
- 9.2B From Hugging Face
- Quantisation
- 6-bit Gemma-2-9B-It-SPPO-Iter3-mixed-4-6-bit
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.5 GB Weights, estimated
- Downloads
- 43 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 11 GB at 6-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-SPPO-Iter3-mixed-4-6-bit --prompt "Hello"MLX builds
2 on mlx-community| Gemma-2-9B-It-SPPO-Iter3-mixed-4-6-bit | 6-bit | 7.5 GB | 11 GB | 43 |
|---|---|---|---|---|
| Gemma-2-9B-It-SPPO-Iter3-8bit | 8-bit | 9.8 GB | 13 GB | 30 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.