← DeepSeek family

DeepSeek-R1-Distill-Llama-8B

A small reasoning model distilled from DeepSeek-R1 onto Llama 3.1 8B.

Overview

DeepSeek-R1-Distill-Llama-8B is a reasoning model made by fine-tuning Llama 3.1 8B on answers from DeepSeek-R1. It works through problems step by step before answering and runs on a single GPU or a CPU. DeepSeek's changes are MIT-licensed, but Meta's Llama 3.1 licence also applies.

Model specifications
WeightsOpen
Parameters8B
Context window128K tokens
LicenceMIT
Commercial useYes

LLM hosts that offer DeepSeek-R1-Distill-Llama-8B

All hosts →
LLM hostHosting planHosting typePricing
xCloudxCloud LocalAI HostingGPU cloudFrom US$59.99Monthly subscription
xCloudxCloud Ollama HostingGPU cloudFrom US$59.99Monthly subscription