MLX Community · First MLX build 18 Jul 2024
Mistral-Nemo-Instruct-2407
MLX
apache-2.0
A 12B parameter model, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 12B From Hugging Face
- Quantisation
- 4-bit Mistral-Nemo-Instruct-2407-4bit
- Memory needed
- 10 GB Estimate, unified memory
- Download
- 6.9 GB Weights, estimated
- Downloads
- 5.9K This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 10 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
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/Mistral-Nemo-Instruct-2407-4bitMLX builds
3 on mlx-community| Mistral-Nemo-Instruct-2407-4bit | 4-bit | 6.9 GB | 10 GB | 5.9K |
|---|---|---|---|---|
| Mistral-Nemo-Instruct-2407-8bit | 8-bit | 13.0 GB | 17 GB | 288 |
| Mistral-Nemo-Instruct-2407-bf16 | bf16 | 24.5 GB | 30 GB | 72 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.