MLX Community · First MLX build 27 Mar 2024
conikeec-deepseek-coder-6.7b-instruct
MLX
deepseek
A 6.7B parameter model, with one MLX build.
- Parameters
- 6.7B From Hugging Face
- Quantisation
- Unstated conikeec-deepseek-coder-6.7b-instruct
- Memory needed
- 32 GB Estimate, unified memory
- Download
- 26.7 GB Weights, estimated
- Downloads
- 116 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 32 GB at Unstated
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/conikeec-deepseek-coder-6.7b-instructMLX builds
1 on mlx-community| conikeec-deepseek-coder-6.7b-instruct | Unstated | 26.7 GB | 32 GB | 116 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.