Qwen3-Coder Advanced Model Released: Alibaba’s Qwen Launches Its Most Powerful Agentic Code Model Yet ‘Qwen3-Coder-480B-A35B-Instruct’ As Open-Source
Alibaba’s AI company Qwen has released its most powerful agentic code model yet, ‘Qwen3-Coder-480B-A35B-Instruct’, as open-source. This advanced Mixture-of-Experts model features 480 billion parameters (35B active) and supports up to 1 million context length through extrapolation, said the company.
Alibaba's AI company Qwen launched its most advanced agent code model yet called 'Qwen3-Coder'. The company said, "We’re releasing Qwen3-Coder-480B-A35B-Instruct, our most powerful open agentic code model to date. " Qwen further mentioned that the new advanced agent code model was a 480B-parameter Mixture-of-Expert (MoE) model (35B active). The Qwen3-Coder-480B-A35B-Instruct natively supports 256K context and scales to 1M context with extrapolation. Qwen3-Coder is an open-source model. ChatGPT Agent Tool Rolling Out to macOS App After Rolling Out to Pro, Plus and Teams Users.
Qwen3-Code Open-Source Model Agentic Code Launched
🚀 Meet Qwen3-Coder, our most advanced agentic code model yet! Kicking off with the open-sourced model Qwen3-Coder-480B-A35B-Instruct, a 480B MoE with 32B active parameters for top coding & agentic tasks. Plus, we're open-sourcing Qwen Code, a CLI tool for agentic programming!… https://t.co/pxCdhIpAoF
— Alibaba Group (@AlibabaGroup) July 22, 2025
(The above story first appeared on LatestLY on Jul 23, 2025 11:18 AM IST. For more news and updates on politics, world, sports, entertainment and lifestyle, log on to our website latestly.com).
