Mistral-NeMo-Minitron-8B-Instruct-4bit
mlx-community/Mistral-NeMo-Minitron-8B-Instruct-4bit
Text generation · transformers
4-bit Open on Hugging Face
Parameters
8.4B
Weights (est.)
≈ 4.7 GB
Mac memory (est.)
8 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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Mistral-NeMo-Minitron-8B-Instruct-4bit --prompt "Hello"
Details
- Base model
- nvidia/Mistral-NeMo-Minitron-8B-Base (finetune)
- Vendor
- NVIDIA
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- nvidia-community-model-license
- Downloads
- 74 in the last 30 days · 927 all time · 1 likes
- Published
- 2024-10-04 · updated 2024-10-04 (2y ago)
- Tags
- mistral
Other MLX builds of nvidia/Mistral-NeMo-Minitron-8B-Base
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Mistral-NeMo-Minitron-8B-Instruct-4bit (this one) | 4-bit | ≈ 4.7 GB | 8 GB+ | 74 |
| Mistral-NeMo-Minitron-8B-Instruct-8bit | 8-bit | ≈ 8.9 GB | 16 GB+ | 51 |
| Mistral-NeMo-Minitron-8B-Instruct | — | ≈ 16.8 GB | 24 GB+ | 52 |