ReasoningMITOpen weights
DeepSeek R1
DeepSeek · DeepSeek
Open model family commonly used as a reference point for reasoning-heavy open-weight workflows.
Best for
Reasoning experiments, coding workflows, and evaluating open reasoning models against closed alternatives.
Tradeoffs
Reasoning traces and latency can be expensive; use smaller distillations for local experimentation.
Local hardware notes
Full model is server-class; distilled variants are better for consumer GPUs.
Local workflow notes
Can be tested locally through smaller distilled or quantized variants; the full model is better suited to server-class hardware.
Local runtimes: Ollama for distills, vLLM, SGLang, llama.cpp community builds
Platforms: Windows, macOS, Linux, Self-hosted servers
HardwareServer-classRuntimevLLM, SGLang, Ollama for distills, hosted providersContextCheck current DeepSeek model cardUpdated2026
DeepSeek on Hugging Face →