Huihui-gemma-3-270m-it-abliterated-8bit
mlx-community/Huihui-gemma-3-270m-it-abliterated-8bit
Text generation · transformers
8-bit Open on Hugging Face
Parameters
268M
Weights (est.)
≈ 285 MB
Mac memory (est.)
8 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/Huihui-gemma-3-270m-it-abliterated-8bit --prompt "Hello"
Details
- Base model
- huihui-ai/Huihui-gemma-3-270m-it-abliterated (quantized)
- Vendor
- huihui-ai
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- gemma
- Downloads
- 38 in the last 30 days · 605 all time · 0 likes
- Published
- 2025-09-27 · updated 2025-09-27 (1y ago)
- Tags
- gemma3_text, gemma3, gemma, google, generated_from_trainer, abliterated, uncensored, mlx-my-repo
Other MLX builds of huihui-ai/Huihui-gemma-3-270m-it-abliterated
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Huihui-gemma-3-270m-it-abliterated-4bit | 4-bit | ≈ 151 MB | 8 GB+ | 50 |
| Huihui-gemma-3-270m-it-abliterated-6bit | 6-bit | ≈ 218 MB | 8 GB+ | 42 |
| Huihui-gemma-3-270m-it-abliterated-8bit (this one) | 8-bit | ≈ 285 MB | 8 GB+ | 38 |
| Huihui-gemma-3-270m-it-abliterated-fp16 | fp16 | ≈ 536 MB | 8 GB+ | 34 |