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

Model Library/Qwen/Qwen3 30B A3B Instruct 2507
Quen Logo Mark

Qwen3 30B A3B Instruct 2507

Ready
Deploy on Demand
Fine-tune
model path:accounts/fireworks/models/qwen3-30b-a3b-instruct-2507

Updated FP8 version of Qwen3-30B-A3B non-thinking mode, with better tool use, coding, instruction following, logical reasoning and text comprehension capabilities

Qwen3 30B A3B Instruct 2507 API Features

Fine-tuning

Docs

Qwen3 30B A3B Instruct 2507 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 30B A3B Instruct 2507 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
7/29/2025
Kind
Base model
Provider
Qwen
Hugging Face
Qwen/Qwen3-30B-A3B-Instruct-2507-FP8

Specification

Calibrated
Yes
Mixture-of-Experts
Yes
Parameters
30.5B

Supported Functionality

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