LLM ReferenceLLM Reference

DeepSeek R1 Distill Llama 8B

Open Source

About

Distilled DeepSeek R1 reasoning encoded into Llama 8B architecture.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Providers(2)

Compare all →
ProviderInput (per 1M)Output (per 1M)Type
Fireworks AI$0.2$0.2Serverless
NVIDIA NIMServerless

Rankings

Specifications

Released2025-01-20
Parameters8B
Context128K
ArchitectureDecoder Only
Specializationgeneral
Trainingmultistage
Fine-tuningtask_specific

Created by

Advancing artificial general intelligence (AGI).

Hangzhou, Zhejiang, China
Founded 2023
Website