Skip to main content
Local LLM Guide

Model

DeepSeek-R1-0528

Check the model’s supported formats and setup instructions before choosing a download. Memory requirement not supplied; check the model and app instructions. Best use: Explaining the original R1 reasoning model and separating cloud/server use from local distills for beginners.

671B total / 37B activeReasoning

Best use

Explaining the original R1 reasoning model and separating cloud/server use from local distills for beginners.

Memory planning

Memory requirement not supplied; check the model and app instructions

Expected pace

Depends on your hardware, app, and conversation length

License

MIT; read the model’s terms before use

Who should use this model?

  • Explaining the original R1 reasoning model and separating cloud/server use from local distills for beginners.

Choose something else when

  • You expect an ordinary Mac, gaming PC, or small GPU to run it well locally.

What hardware makes sense?

The download is only part of the memory needed. Leave room for the app, the input it processes, and other open programs. For chat models, context includes the instructions, conversation, and answer. Longer context needs more memory.

CPU only
Use a smaller model for this memory limit.
8GB system memory
Check this model with your exact hardware and settings before choosing it.
16GB system memory
Check this model with your exact hardware and settings before choosing it.
32GB system memory
Check this model with your exact hardware and settings before choosing it.
8GB GPU memory
Check this model with your exact hardware and settings before choosing it.
12GB GPU memory
Check this model with your exact hardware and settings before choosing it.
24GB GPU memory
Check this model with your exact hardware and settings before choosing it.
Apple unified memory
Check this model with your exact hardware and settings before choosing it.

Model facts that change the decision

Parameters
671B total / 37B active
Input
Text
Published context limit
128,000 tokens
Model format
safetensors · GGUF · Ollama
Languages
Unknown

First setup

Ollama

ollama run deepseek-r1:671b

llama.cpp

Use a cited GGUF build with current llama.cpp-compatible tooling.

Conditions that change the answer

  • Not practical for normal local users.
  • Use distilled 8B, 14B, or 32B variants instead.
  • Long-context and full-weight deployment require specialized server infrastructure.
  • Censorship and political-bias caveats still matter.
  • Commercial use: Allowed under MIT license.
  • Full DeepSeek-R1-0528 is a server-class reasoning reference model, not a beginner local download. List it only to explain the source teacher model behind distills and to set expectations about hardware, speed, and censorship caveats clearly.

Read the controlling license text →