4-bit Open on Hugging Face
Parameters
7.4B
Weights (est.)
≈ 4.1 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-7B-chat-MLX-4bit --prompt "Hello"
Details
- Base model
- Rakuten/RakutenAI-7B-chat (quantized)
- Vendor
- Rakuten
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 27 in the last 30 days · 175 all time · 0 likes
- Published
- 2026-03-20 · updated 2026-03-20 (7mo ago)
- Languages
- en, ja
- Tags
- mistral
Other MLX builds of Rakuten/RakutenAI-7B-chat
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| RakutenAI-7B-chat-MLX-4bit (this one) | 4-bit | ≈ 4.1 GB | 8 GB+ | 27 |
| RakutenAI-7B-chat-MLX-8bit | 8-bit | ≈ 7.8 GB | 16 GB+ | 29 |