8-bit Open on Hugging Face
Parameters
1.4B
Weights (est.)
≈ 1.5 GB
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/sarashina2.1-1b-sft-8bit --prompt "Hello"
Details
- Base model
- Aratako/sarashina2.1-1b-sft (quantized)
- Vendor
- Aratako
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- other
- Downloads
- 22 in the last 30 days · 309 all time · 0 likes
- Published
- 2024-12-11 · updated 2024-12-11 (1y ago)
- Languages
- ja
- Tags
- llama, axolotl, generated_from_trainer
Other MLX builds of Aratako/sarashina2.1-1b-sft
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| sarashina2.1-1b-sft-4bit | 4-bit | ≈ 792 MB | 8 GB+ | 27 |
| sarashina2.1-1b-sft-8bit (this one) | 8-bit | ≈ 1.5 GB | 8 GB+ | 22 |
| sarashina2.1-1b-sft | — | ≈ 2.8 GB | 8 GB+ | 20 |