Qwen3 30B A3B Thinking 2507 by ModelScope

Discuss

Model details

Qwen3 30B A3B Thinking 2507

ModelScopeQwen/Qwen3-30B-A3B-Thinking-2507qwen

Open provider page Provider docs

Quick Info

Provider: ModelScope
Model key: Qwen/Qwen3-30B-A3B-Thinking-2507
Release date: Jul 30, 2025

Cost

A provider subscription or plan supersedes token-based pricing for this model.

Limits

Output tokens: 32,768 tokens
Context window: 262,144 tokens

Latest news about Qwen3 30B A3B Thinking 2507

No articles yet. Fetch the latest news to show it here.

Videos about Qwen3 30B A3B Thinking 2507

Recent tweets and retweets from ModelScope

Jul 18, 2026, 3:40 AMUTC

Great to catch up with so many friends from the OSS community in Shanghai yesterday. Looking forward to more collaborations!

Jul 17, 2026, 7:38 AMUTC

InternVLA-A1.5 brings latent foresight to robot control, with four checkpoints now available on ModelScope. 🚀 🤖 modelscope.ai/collections/In… 📄 modelscope.ai/papers/2607.04… 🏆 Reported best overall results across six simulation benchmarks, including 98.9 on LIBERO, 84.8…

Jul 17, 2026, 2:30 AMUTC

One of the most anticipated open-weight releases is coming soon 🚀 ModelScope will provide Day 0 support for Kimi K3. Stay tuned!👀

Jul 17, 2026, 2:06 AMUTC

Robot rollouts are no longer all-or-nothing. VLAC-Cut is now on ModelScope, turning long execution videos into reusable post-training segments. ✂️ 🤖 modelscope.ai/models/InternR… 📄 modelscope.ai/papers/2607.09… 🏆 In the reported four-task pipeline, final policies reach…

Jul 16, 2026, 5:00 PMUTC

SenseNova-U1-Infographic-V3 turns infographic creation into a generate-and-edit workflow. 🚀 🤖 modelscope.ai/models/SenseNo… 📄 modelscope.ai/papers/2605.12… 🧠 Model: an 8B-MoT checkpoint built on the native multimodal NEO-unify architecture. 📊 Strong T2I foundation:…