mixtral-8x22b-instruct-oh-4bit
mlx-community/mixtral-8x22b-instruct-oh-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
141B
Weights (est.)
≈ 79.4 GB
Mac memory (est.)
96 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
- mistral-community/Mixtral-8x22B-v0.1 (finetune)
- Vendor
- mistral-community
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 41 in the last 30 days · 857 all time · 0 likes
- Published
- 2024-04-12 · updated 2024-04-17 (2y ago)
- Languages
- en
- Tags
- mixtral
Other MLX builds of mistral-community/Mixtral-8x22B-v0.1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| dolphin-2.9.1-mixtral-1x22b-2bit | 2-bit | ≈ 7.0 GB | 16 GB+ | 33 |
| dolphin-2.9.1-mixtral-1x22b-4bit | 4-bit | ≈ 12.5 GB | 16 GB+ | 25 |
| dolphin-2.9.1-mixtral-1x22b-8bit | 8-bit | ≈ 23.6 GB | 32 GB+ | 26 |
| mixtral-8x22b-instruct-oh-4bit (this one) | 4-bit | ≈ 79.4 GB | 96 GB+ | 41 |
| zephyr-orpo-141b-A35b-v0.1-4bit | 4-bit | ≈ 79.4 GB | 96 GB+ | 39 |
| zephyr-orpo-141b-A35b-v0.1-8bit | 8-bit | ≈ 150 GB | 192 GB+ | 32 |