AI BriefingQwen news
The latest AI and developer news from Qwen, with short summaries.
Visit website →Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All
A coding agent model, Qwen3.6-35B-A3B, has been released for anyone to use.
Qwen3.6-Plus: Toward Real-World Agents
Qwen3.6-Plus has launched with a 1M token context and enhanced agentic coding.
Qwen3.5-Omni: Scaling Up Toward Native Omni-Modal AGI
Qwen3.5-Omni significantly boosts omnimodal performance with a 256k context, 10-hour audio input, and 113-language ASR.
Qwen3.5-Max-Preview Unveiled on Arena
Qwen3.5-Max-Preview has been deployed on Arena and shown strong performance in preliminary evaluations.
Qwen3.5: Toward Native Multimodal Agents
Qwen3.5-397B-A17B has been released, a native multimodal model in which only 17B of the 397B parameters are activated.
Qwen-Image-2.0: Professional Infographics, Outstanding Photorealism
Qwen-Image-2.0 integrates PPTs, posters, and photos into a single model with 1k-token instructions and 2K resolution.
Qwen3-Coder-Next: The Evolution of a Small Hybrid Model Aimed at Agentic Coding
Qwen3-Coder-Next targets SWE-Bench Pro-level performance with just 3B active parameters.
Qwen3-ASR and Qwen3-ForcedAligner Open-Sourced: Robust Streaming Multilingual Support
Qwen3-ASR and ForcedAligner have been open-sourced, strengthening multilingual and streaming speech recognition.
Breaking Through the Limits of Qwen3-Max-Thinking
Qwen3-Max-Thinking boosts reasoning performance through tool use and test-time scaling.
Qwen3-TTS Family Released as Open Source: Voice Design, Cloning, and Generation
Qwen3-TTS has been released with a 1.7B and 0.6B lineup, supporting voice design, voice cloning, and streaming generation.
Qwen3-VL-Embedding and Qwen3-VL-Reranker: Models for Next-Generation Multimodal Search
Qwen has released two multimodal search models that handle text, images, and video together.
Qwen-Image-2512: More Refined Details, Higher Realism
Qwen-Image-2512 significantly improves human realism, natural detail, and text rendering.
Qwen-Image-Edit-2511: Improved Consistency
Qwen-Image-Edit-2511 reduces image drift and significantly improves single- and multi-person consistency.
Qwen3-TTS Evolves: Voice Cloning and Voice Design
Qwen3-TTS now supports natural language voice design and 3-second voice cloning.
Qwen-Image-Layered: Essential Editability Achieved Through Layer Decomposition
It decomposes an image into RGBA layers so each element can be edited independently.
Qwen3-Omni-Flash-2025-12-01: An Upgrade That Listens, Sees, and Follows More Intelligently
**Qwen3-Omni-Flash-2025-12-01** has been upgraded to handle speech, vision, and text more reliably across the board.
SAPO: A Stable, High-Performance Reinforcement Learning Method for Training Large Language Models
SAPO stabilizes LLM reinforcement learning by using smooth gating instead of hard clipping.
Qwen3-TTS Update! 49 Voices + 10 Languages + 9 Dialects
Qwen3-TTS-Flash now supports 49 voices, 10 languages, and 9 dialects.
Qwen3Guard: Real-Time Safety for Token Streams
Qwen3Guard is a safety guardrail that judges prompts and responses in real time.
Qwen-Image-Edit: Higher Quality and More Efficient Image Editing
Qwen-Image-Edit is a 20B model that extends Qwen-Image's text rendering into image editing.