Skip to content

DeepSeek R1 7B

MIT

DeepSeek · 7B · transformer-decoder

2025-01-20 131K context 7B params

Use Cases

chat code reasoning math

Quantization Options

QuantBitsVRAMQualityStatus
Q4_K_M45.7 GBModerate
Q8_0rec89.0 GBGood
F161616.0 GBExcellent

About this model

DeepSeek R1 7B is a distilled reasoning model from DeepSeek's R1 series, based on the Qwen 2.5 architecture. It inherits chain-of-thought reasoning capabilities from the larger DeepSeek R1 model through knowledge distillation, delivering strong reasoning performance at a compact size. This model excels at mathematical problem solving, logical reasoning, and coding tasks. It shows its reasoning process step by step, making it transparent and useful for educational and analytical purposes. It runs efficiently on consumer hardware.

Benchmarks

68.5
mmlu