DeepSeek Coder Models — Hardware Requirements

9 DeepSeek Coder models from DeepSeek and the community, from the smallest that runs in 1.3 GB of VRAM up to 235.7B parameters. Every row links to full quantization tables and GPU compatibility.

All DeepSeek Coder Models by Size

ModelParamsContext
Deepseek Coder 1.3B Base1.3B16K
Deepseek Coder 1.3B Instruct1.3B16K
Deepseek Coder 1.3B Kexer1.3B16K
Deepseek Coder 6.7B Instruct6.7B16K
Deepseek Coder 7B Instruct V1.56.9B4K
DeepSeek Coder v2 Lite Instruct15.7B164K
DeepSeek Coder v2 Lite Base15.7B164K
Deepseek Coder 33B Instruct33.3B16K
DeepSeek Coder v2 Instruct235.7B164K

Frequently Asked Questions

How much VRAM do I need to run a DeepSeek Coder model?
The smallest DeepSeek Coder model, Deepseek Coder 1.3B Base, runs from 1.3 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which DeepSeek Coder models can I run on a 16 GB GPU?
8 of 9 DeepSeek Coder models fit in 16 GB of VRAM at some quantization, including Deepseek Coder 6.7B Instruct, DeepSeek Coder v2 Lite Instruct, Deepseek Coder 33B Instruct.
What is the most popular DeepSeek Coder model to run locally?
Deepseek Coder 6.7B Instruct is the most downloaded DeepSeek Coder model in local-friendly quantized formats. It runs from 4.2 GB of VRAM.