Open-weight reasoning model matching o1
DeepSeek R1 is a pure reasoning model trained with reinforcement learning on chain-of-thought traces. It matches OpenAI's o1 on math and coding benchmarks while being open-weight and significantly cheaper to run via API.
Try DeepSeek R1Sourced from official model cards and academic papers. Higher is better.
Download and run this model on your own hardware — no API key or internet required after setup.
Ollama
TerminalRun this command in your terminal. Ollama downloads and manages the model locally.
ollama pull deepseek-r1:14b