GLM 5.2 is live! Opus-level intelligence at open-source rates. Pay per token on serverless. Try it today.

Model Library/Qwen/Qwen3 4B
Quen Logo Mark

Qwen3 4B

Ready
Deploy on Demand
Fine-tune
model path:accounts/fireworks/models/qwen3-4b

Latest Qwen3 state of the art model, 4B model

Qwen3 4B API Features

Fine-tuning

Docs

Qwen3 4B can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model

On-demand Deployment

Docs

On-demand deployments allow you to use Qwen3 4B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
4/28/2025
Kind
Base model
Provider
Qwen
Hugging Face
Qwen/Qwen3-4B

Specification

Calibrated
No
Mixture-of-Experts
No
Parameters
4.41B

Supported Functionality

Fine-tuning
Supported
Serverless
Not supported
Context Length
40.9k tokens
Function Calling
Supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Not supported