{"slug":"ornith-1-5","name":"Ornith-1.5","nameZh":"Ornith-1.5（9B / 35B-A3B 自我改进开源模型）","category":"models","categoryName":"Open-weight models","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"MIT","maintained":"yes","officialUrl":"https://huggingface.co/ornith-ai/Ornith-1.5-9B","repo":null,"latestVersion":null,"latestRelease":null,"stars":null,"starsAsOf":null,"description":"Ornith AI’s open models built on Qwen3.5 / Gemma4 with continued pre-/mid-/post-training, extending self-improvement to generating tasks, building scaffolds and RL on rollouts; the 9B dense model fits one GPU (with a mobile quantised variant), 35B-A3B is the MoE version; official GGUFs. MIT (check base-model terms too)","descriptionZh":"Ornith AI 的开源模型系列，在 Qwen3.5 / Gemma4 基础上继续预训练和后训练，把自我改进循环扩展到“自动出题 + 搭建解题脚手架 + 强化学习”；9B 稠密版可单卡部署，另有手机量化版，35B-A3B 为 MoE 版，官方提供 GGUF。MIT 许可（基座许可请一并核对）","callMethods":[],"platforms":[],"addedAt":"2026-10-21","updatedAt":null,"topics":[],"language":null,"lastPush":null,"formerly":null,"packages":[],"recentVersions":[],"alternatives":["deepseek-v3","qwen3","gpt-oss","qwen3-coder","kimi-k2","llama-models","ultralytics","gemma"],"stacks":[],"scenarios":[],"problems":[],"reasonZh":null,"sources":["editorial"],"record":"https://aimap.page/api/v1/software/ornith-1-5.json","pages":{"en":"https://aimap.page/en/software/ornith-1-5/","zh-hans":"https://aimap.page/zh-hans/software/ornith-1-5/"}}