Rakuten · First MLX build 19 Feb 2025
RakutenAI-2.0-8x7B-instruct
MLX
apache-2.0
A 47B parameter model from Rakuten, with 2 MLX builds at 4-bit.
- Parameters
- 47B From Hugging Face
- Quantisation
- 4-bit RakutenAI-2.0-8x7B-instruct-4bit
- Memory needed
- 32 GB Estimate, unified memory
- Download
- 26.3 GB Weights, estimated
- Downloads
- 42 This build, last 30 days
- Task
- —
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 32 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/RakutenAI-2.0-8x7B-instruct-4bitMLX builds
2 on mlx-community| RakutenAI-2.0-8x7B-instruct-4bit | 4-bit | 26.3 GB | 32 GB | 42 |
|---|---|---|---|---|
| RakutenAI-2.0-8x7B-instruct | Unstated | 93.7 GB | 107 GB | 15 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.