RakutenAI-2.0-8x7B-instruct-4bit
mlx-community/RakutenAI-2.0-8x7B-instruct-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
47B
Weights (est.)
≈ 26.3 GB
Mac memory (est.)
32 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.
Details
- Base model
- Rakuten/RakutenAI-2.0-8x7B-instruct (quantized)
- Vendor
- Rakuten
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 41 in the last 30 days · 640 all time · 2 likes
- Published
- 2025-02-19 · updated 2025-02-19 (1y ago)
- Languages
- en, ja
- Tags
- mixtral
Other MLX builds of Rakuten/RakutenAI-2.0-8x7B-instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| RakutenAI-2.0-8x7B-instruct-4bit (this one) | 4-bit | ≈ 26.3 GB | 32 GB+ | 41 |
| RakutenAI-2.0-8x7B-instruct | — | ≈ 93.7 GB | 128 GB+ | 15 |