8-bit Open on Hugging Face
Parameters
9.2B
Weights (est.)
≈ 9.8 GB
Mac memory (est.)
16 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Gemma-2-9B-It-SPPO-Iter3-8bit --prompt "Hello"
Details
- Base model
- UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3 (quantized)
- Vendor
- UCLA-AGI
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- gemma
- Downloads
- 30 in the last 30 days · 392 all time · 0 likes
- Published
- 2025-07-22 · updated 2025-07-22 (1y ago)
- Languages
- en
- Tags
- gemma2
Other MLX builds of UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Gemma-2-9B-It-SPPO-Iter3-mixed-4-6-bit | 6-bit | ≈ 7.5 GB | 16 GB+ | 44 |
| Gemma-2-9B-It-SPPO-Iter3-8bit (this one) | 8-bit | ≈ 9.8 GB | 16 GB+ | 30 |