IQuest Research just open-sourced IQuest-Q1🚀
A 320B-parameter MoE model, with 15B parameters activated per token.
It is built for agentic coding, reasoning, and multi-step tool use.
With a 524K-token context window, IQuest-Q1 can:
• Generate interactive web apps from natural-language instructions
• Inspect existing code and training environments to find and fix issues
• Execute multi-step tasks across tool-rich environments, continuously reading context, calling tools, and adjusting its actions
IQuest-Q1 lands with 320B MoE scale, 15B active parameters, and a 512K context window for long-horizon coding agents.
🤖
🧠 Built for agentic coding, complex reasoning, and multi-step tool use across long-running workflows.
🏆 Scores 84.5 on CyberGym, 83.2 on Terminal-Bench 2.1, 64.6 on DeepSWE v1.1, and 63.0 on NL2Repo.
⚡ 256 experts with 8 activated per token, hybrid sliding-window/full attention, and recursive MTP for faster decoding.
🛠️ Production deployment supports SGLang and vLLM, with integrations for Claude Code, Codex CLI, and OpenAI-compatible APIs.
📜 Weights released under the IQuest-Q1 License.