4-bit Open on Hugging Face
Parameters
1.3B
Weights (est.)
≈ 732 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/gemma-3-1b-it-qat-4bit --prompt "Hello"
Details
- Base model
- google/gemma-3-1b-it (quantized)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- gemma
- Downloads
- 23K in the last 30 days · 760K all time · 6 likes
- Published
- 2025-04-15 · updated 2025-04-18 (1y ago)
- Tags
- gemma3_text
Other MLX builds of google/gemma-3-1b-it
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-3-1b-it-qat-4bit (this one) | 4-bit | ≈ 732 MB | 8 GB+ | 23K |
| gemma-3-1b-it-4bit | 4-bit | ≈ 732 MB | 8 GB+ | 7.3K |
| gemma-3-1b-it-4bit-DWQ | 4-bit DWQ | ≈ 732 MB | 8 GB+ | 848 |
| gemma-3-1b-it-DQ | 4-bit | ≈ 732 MB | 8 GB+ | 44 |
| gemma-3-1b-it-6bit | 6-bit | ≈ 1.1 GB | 8 GB+ | 53 |
| gemma-3-1b-it-qat-6bit | 6-bit | ≈ 1.1 GB | 8 GB+ | 29 |
| gemma-3-1b-it-8bit | 8-bit | ≈ 1.4 GB | 8 GB+ | 146 |
| gemma-3-1b-it-qat-8bit | 8-bit | ≈ 1.4 GB | 8 GB+ | 99 |
| gemma-3-1b-it-bf16 | bf16 | ≈ 2.6 GB | 8 GB+ | 1.6K |
| gemma-3-1b-it-qat-bf16 | bf16 | ≈ 2.6 GB | 8 GB+ | 36 |