dolphin-2.8-mistral-7b-v02-8bit
mlx-community/dolphin-2.8-mistral-7b-v02-8bit
Uncategorised · mlx
8-bit Open on Hugging Face
Parameters
7.2B
Weights (est.)
≈ 7.8 GB
Mac memory (est.)
16 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/Mistral-7B-v0.2 (finetune)
- Vendor
- mistral-community
- Task
- Uncategorised
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 22 in the last 30 days · 448 all time · 0 likes
- Published
- 2024-04-06 · updated 2024-04-06 (2y ago)
- Languages
- en
- Tags
- mistral, model-index
Other MLX builds of mistral-community/Mistral-7B-v0.2
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| dolphin-2.8-mistral-7b-v02-4bit | 4-bit | ≈ 4.3 GB | 8 GB+ | 52 |
| dolphin-2.8-mistral-7b-v02-8bit (this one) | 8-bit | ≈ 7.8 GB | 16 GB+ | 22 |
| dolphin-2.8-mistral-7b-v02 | — | ≈ 14.5 GB | 24 GB+ | 54 |