DeepSeek R1 7B
DeepSeekCompact reasoning model distilled from DeepSeek-R1, offering strong chain-of-thought reasoning in a small package. Great for local deployment with limited hardware.
Parameters 7B
Min VRAM 6 GB
Recommended VRAM 8 GB
Context Length 128K
License MIT
🚀 Get Started
Run DeepSeek R1 7B locally with one command:
ollama run deepseek-r1:7b Requires Ollama installed.
📊 Benchmarks
BenchmarkScore
MMLU 58.7
GSM8K 74.5
HumanEval 62.2
💻 Hardware Recommendations
🟢 Minimum
6 GB VRAM GPU or 12+ GB RAM (CPU mode)
Expect slower generation in CPU mode
🔵 Recommended
8 GB VRAM GPU
Fast generation with room for context