8-bit Open on Hugging Face
Parameters
1.5B
Weights (est.)
≈ 1.6 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/RakutenAI-2.0-mini-MLX-8bit --prompt "Hello"
Details
- Base model
- Rakuten/RakutenAI-2.0-mini (quantized)
- Vendor
- Rakuten
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 46 in the last 30 days · 267 all time · 1 likes
- Published
- 2026-03-20 · updated 2026-03-20 (7mo ago)
- Languages
- en, ja
- Tags
- mistral
Other MLX builds of Rakuten/RakutenAI-2.0-mini
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| RakutenAI-2.0-mini-MLX-4bit | 4-bit | ≈ 863 MB | 8 GB+ | 39 |
| RakutenAI-2.0-mini-MLX-8bit (this one) | 8-bit | ≈ 1.6 GB | 8 GB+ | 46 |