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

Qwen3 Coder 30B A3B Instruct

Ready
model path:accounts/fireworks/models/qwen3-coder-30b-a3b-instruct
Deploy on demand

Latest Qwen3 coder model, 30B with 3B active parameter model

Qwen3 Coder 30B A3B Instruct API Features

On-demand Deployment

Docs

On-demand deployments allow you to use Qwen3 Coder 30B A3B Instruct on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
1 AUG, 2025
Kind
Base model
Provider
Qwen
Huggingface
Qwen/Qwen3-Coder-30B-A3B-Instruct

Specifications

Calibrated
Yes
Mixture-of-Experts
Yes
Parameters
30.5B

Supporting Functionality

Fine-tuning
Not Supported
Serverless
Not Supported
Context Length
262k tokens
Function Calling
Not Supported
Embeddings
Not Supported
Rerankers
Not Supported
Supporting image input
Not Supported

Qwen3 Coder 30B A3B Instruct FAQs

Qwen3-Coder 30B A3B Instruct is a Mixture-of-Experts (MoE) instruction-tuned coding model developed by Qwen (Alibaba Group). It features 30.5 billion total parameters with 3.3 billion active per forward pass, and is trained for advanced code reasoning, agentic systems, and browser-integrated coding tasks.