NewJoin us for the Forge keynote livestream on November 3rd
DocsLog inGet started
Deepseek logo

DeepSeek R1 Distill Qwen 32B

Ready
model path:accounts/fireworks/models/deepseek-r1-distill-qwen-32b
Deploy on demand

Qwen 32B distilled with reasoning from Deepseek R1

DeepSeek R1 Distill Qwen 32B API Features

On-demand Deployment

Docs

On-demand deployments allow you to use DeepSeek R1 Distill Qwen 32B 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-Qwen-32B

Specifications

Calibrated
No
Mixture-of-Experts
No
Parameters
32.7B

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