MLX Community · First MLX build 16 Jul 2024
DeepSeek-Coder-V2-Lite-Instruct
MLX
deepseek-license Trending
A 16B parameter model, with 2 MLX builds, from 4-bit to 8-bit.
- Parameters
- 16B From Hugging Face
- Quantisation
- 4-bit DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx
- Memory needed
- 12 GB Estimate, unified memory
- Download
- 8.8 GB Weights, estimated
- Downloads
- 3.7K This build, last 30 days
- Task
- —
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 12 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/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlxMLX builds
2 on mlx-community| DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx | 4-bit | 8.8 GB | 12 GB | 3.7K |
|---|---|---|---|---|
| DeepSeek-Coder-V2-Lite-Instruct-8bit | 8-bit | 16.7 GB | 21 GB | 1.0K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.