Get the latest tech news

DeepSeek’s distilled new R1 AI model can run on a single GPU


DeepSeek's distilled new R1 AI model can run on a single GPU, putting it within reach of hobbyists.

But the Chinese AI lab also released a smaller, “distilled” version of its new R1, DeepSeek-R1-0528-Qwen3-8B, that DeepSeek claims beats comparably-sized models on certain benchmarks. The smaller updated R1, which was built using the Qwen3-8B model Alibaba launched in May as a foundation, performs better than Google’s Gemini 2.5 Flash on AIME 2025, a collection of challenging math questions. DeepSeek-R1-0528-Qwen3-8B also nearly matches Microsoft’s recently released Phi 4 reasoning plus model on another math skills test, HMMT.

Get the Android app

Or read this on TechCrunch

Read more on:

Photo of GPU

GPU

Photo of DeepSeek

DeepSeek

Photo of single GPU

single GPU

Related news:

News photo

DeepSeek’s updated R1 AI model is more censored, test finds

News photo

China’s DeepSeek quietly releases upgraded R1 AI model, ramping up competition with OpenAI

News photo

DeepSeek Says Upgraded Model Reasons Better, Hallucinates Less