Skip to content

DeepSeek R1 1.5B

MIT

DeepSeek · 1.5B · transformer-decoder

2025-01-20131K context1.5B params

Use Cases

chatreasoningmath

Quantization Options

QuantBitsVRAMQualityStatus
Q4_K_M42.0 GBModerate
Q8_0rec83.0 GBGood
F16165.0 GBExcellent

About this model

DeepSeek R1 1.5B is a distilled reasoning model based on Qwen 2.5, bringing chain-of-thought reasoning to ultra-lightweight hardware. Despite its tiny size, it shows the characteristic "thinking" behavior of the R1 family on math and logic tasks. At under 3 GB VRAM for Q8, it runs on virtually any hardware — great for edge devices, experimenting with reasoning models, or as a fast local assistant.

Benchmarks

52.0
mmlu