Moyan AI Training Institution LogoMoyan AI

Reasoning & Math Models · Fast-moving · Intermediate

DeepSeek R1 Distill Qwen 32B

Also known as: R1-Distill-32B, DeepSeek Qwen 32B

A 32B parameter reasoning model created by distilling DeepSeek R1 reasoning trajectories into Qwen 2.5 32B.

What DeepSeek R1 Distill Qwen 32B is

Provides top-tier reasoning capabilities in a lightweight 32B footprint playable on single high-end consumer GPUs.

How it works

Fine-tuned on 800k synthetic reasoning trajectories generated by the full DeepSeek R1 model.

Why it matters

Empowers developers to deploy local, private reasoning endpoints for code and logic workloads.

Common uses

  • Local private reasoning servers
  • IDE inline code reasoning
  • Edge mathematical problem solving

More in this collection

Browse all AI Models