4-bit Open on Hugging Face
Parameters
268M
Weights (est.)
≈ 151 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/functiongemma-270m-it-4bit --prompt "Hello"
Details
- Base model
- google/functiongemma-270m-it (quantized)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- gemma
- Downloads
- 619 in the last 30 days · 4.3K all time · 3 likes
- Published
- 2025-12-18 · updated 2025-12-18 (10mo ago)
- Tags
- gemma3_text, gemma3, gemma, google, functiongemma
Other MLX builds of google/functiongemma-270m-it
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| functiongemma-270m-it-4bit (this one) | 4-bit | ≈ 151 MB | 8 GB+ | 619 |
| functiongemma-270m-it-5bit | 5-bit | ≈ 184 MB | 8 GB+ | 36 |
| functiongemma-270m-it-6bit | 6-bit | ≈ 218 MB | 8 GB+ | 42 |
| functiongemma-270m-it-8bit | 8-bit | ≈ 285 MB | 8 GB+ | 58 |
| functiongemma-270m-it-bf16 | bf16 | ≈ 536 MB | 8 GB+ | 133 |