NewJoin us for our inaugural conference, Forge 2026
DocsLog inGet started
Deepseek logo

DeepSeek R1 Distill Llama 8B

Ready
model path:accounts/fireworks/models/deepseek-r1-distill-llama-8b
Deploy on demand

Llama 8B distilled with reasoning from Deepseek R1

DeepSeek R1 Distill Llama 8B API Features

On-demand Deployment

Docs

On-demand deployments allow you to use DeepSeek R1 Distill Llama 8B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
22 JAN, 2025
Kind
Base model
Provider
Deepseek
Huggingface
deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Specifications

Calibrated
Yes
Mixture-of-Experts
No
Parameters
8.03B

Supporting Functionality

Fine-tuning
Not Supported
Serverless
Not Supported
Context Length
131k tokens
Function Calling
Not Supported
Embeddings
Not Supported
Rerankers
Not Supported
Supporting image input
Not Supported