Ministral-8B-Instruct-2410-8bit
mlx-community/Ministral-8B-Instruct-2410-8bit
Uncategorised · vllm
8-bit Open on Hugging Face
Parameters
8.0B
Weights (est.)
≈ 8.5 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
- Ministral-8B-Instruct-2410-HF
- Vendor
- —
- Task
- Uncategorised
- Quantisation
- 8-bit
- Licence
- mrl
- Downloads
- 101 in the last 30 days · 2.1K all time · 2 likes
- Published
- 2024-10-16 · updated 2024-10-17 (2y ago)
- Languages
- en, fr, de, es, it, pt, zh, ja, ru, ko
- Tags
- vllm, mistral
Other MLX builds of Ministral-8B-Instruct-2410-HF
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Ministral-8B-Instruct-2410-4bit | 4-bit | ≈ 4.5 GB | 8 GB+ | 927 |
| Ministral-8B-Instruct-2410-8bit (this one) | 8-bit | ≈ 8.5 GB | 16 GB+ | 101 |
| Ministral-8B-Instruct-2410-bf16 | bf16 | ≈ 16.0 GB | 24 GB+ | 74 |