IQuest-Q1: 320B MoE model generates games from one prompt and debugs RL training
量子位 · wechat · 2026-09-29
IQuestResearch released IQuest-Q1, a decoder-only Transformer with sparse MoE architecture (320B total, 15B active parameters).
Two hands-on tests from the author:
- One-prompt game generation: a 200-character prompt produced a playable vertical-screen HTML game with NPC design, health bars and random reward mechanics.
- Real engineering debugging: using the ClaudeCode CLI framework, the model analyzed RL training logs and trajectories, locating a bug where the inference server inserted an extra space during text decoding—breaking prefix matching and multi-turn generation—and fixed it.
On benchmarks, it performs well among same-scale models on NL2Repo, CyberGym, Terminal-Bench 2.1, DeepSWE v1.1 and JobBench. The team's earlier ModularRSI self-evolution framework hit #2 on the HuggingFace daily leaderboard, lifting Agent accuracy on Terminal-Bench 2.0 and SWE-Bench Verified from 47.57%/73.40% to 52.43%/76.45%. The model is also being used in its own R&D iteration loop.
Related event: IQuest Open-Sources 320B MoE Model Q1 for Agentic Coding(4 posts)→
More from Models
- The endless model-hopper cycle: Claude's success overloads servers, users drift back to GPT — haider1 · 2026-09-29
- MolmoAct 2 tops robot board at 46% success with just 300 demos — DJiafei · 2026-09-29
- Dev argues 'sounds like Claude' models reflect pretraining data leakage, not distillation — menhguin · 2026-09-29
- Rumor: OpenAI Pays $380k-$460k for Control Engineers to Bake Robotics into GPT-6 — xeophon · 2026-09-29
- Same Prompt, Two Eras: GPT-5.5 vs Claude Sonnet 4 Flappy Bird Test Shows 1.5 Years of LLM Gains — Dhakkad_Mutthal · 2026-09-29
- Gemini 3.6 Flash refuses query that Google Search AI answers correctly — magallanes2010 · 2026-09-29