Qwen3 30B A3B Instruct 2507

Qwen3 30B A3B Instruct 2507

Developer	Qwen
Release date	July 28, 2025
Family	Qwen
Generation	Qwen 3
Size class
Context window	262K tokens
Max output	236K tokens
Input	Text
Output	Text
Knowledge cutoff	2025-06-30
Weights	Open weights
License	Apache 2.0
Website	qwen.ai
Links	Model card Docs Hugging Face

Part of a series on

input: $0.10
cached: $0.10
output: $0.30
Context: 262Ktokens
Released: 1y ago
Size: 30Bparameters

Specifications

Model

Developer: Qwen
Family: Qwen Qwen 3
Type: Language model
Released: July 28, 2025
Model ID: qwen/qwen3-30b-a3b-instruct-2507

Capabilities

Input → output: Text → Text
Native context: 256K tokens
Max output: 236K tokens
Tokenizer: Qwen3
Knowledge cutoff: 2025-06-30

Weights

Openness: Open weights
License: Apache 2.0
Size: 30B
Hugging Face: Qwen/Qwen3-30B-A3B-Instruct-2507

Sources:models.devOpenRouter

Metadata synced Nov 3, 2026, 11:17 PM UTC

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.