The right model for every task. Try Nexus
Docs
Log in
Get started
Qwen logo

Qwen3 235B A22B Instruct 2507

Ready
model path:accounts/fireworks/models/qwen3-235b-a22b-instruct-2507
Deploy on demandFine-tune

Updated FP8 version of Qwen3-235B-A22B non-thinking mode, with better tool use, coding, instruction following, logical reasoning and text comprehension capabilities

Qwen3 235B A22B Instruct 2507 API Features

Fine-tuning

Docs

Qwen3 235B A22B 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 235B A22B Instruct 2507 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
21 JUL, 2025
Kind
Base model
Provider
Qwen
Huggingface
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8

Specifications

Calibrated
Yes
Mixture-of-Experts
Yes
Parameters
235B

Supporting Functionality

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

Qwen3 235B A22B Instruct 2507 FAQs

Qwen3-235B-A22B-Instruct-2507 is an instruction-tuned, non-thinking mode large language model developed by Alibaba’s Qwen team. It is a mixture-of-experts (MoE) model with 235 billion total parameters (22B active) and is optimized for reasoning, tool use, coding, and long-context tasks.