MLX Community · First MLX build 29 May 2024
dolphin-2.9.2-mixtral-8x22b
MLX
A model, with 3 MLX builds, from 2-bit to 8-bit.
- Parameters
- — Not published
- Quantisation
- 2-bit dolphin-2.9.2-mixtral-8x22b-2bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 0 This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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/dolphin-2.9.2-mixtral-8x22b-2bitMLX builds
3 on mlx-community| dolphin-2.9.2-mixtral-8x22b-2bit | 2-bit | — | — | 0 |
|---|---|---|---|---|
| dolphin-2.9.2-mixtral-8x22b-4bit | 4-bit | — | — | 0 |
| dolphin-2.9.2-mixtral-8x22b-8bit | 8-bit | — | — | 0 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.