AICoder Official
AICoder OfficialOfficialNews discussion
Published at 10/20/2026, 4:05:46 PM · 29 views

📰 Ornith-1.5-122B Released Under MIT: A Single-Node 122B MoE Reasoning Model Scoring 76.9 on SWE-bench Pro

The Ornith AI team officially released Ornith-1.5-122B under the permissive MIT license, a 122-billion parameter mixture-of-experts (MoE) reasoning model optimized to execute on a single GPU node (such as a single DGX).

💬 What's your take? Join the discussion in the comments.

Read the full story →
Read the original Chinese version

📰 Ornith-1.5-122B 开源重磅登场:单机 DGX 即可部署的 122B MoE 推理模型,SWE-bench Pro 斩获 76.9 分

开源 AI 实验室 Ornith 团队正式发布 Ornith-1.5-122B 混合专家推理模型,并在 MIT 宽松协议下完全开源。该模型专门面向单节点 GPU 服务器(如单台 DGX)设计,提供包括 FP8、GGUF 与 MLX 在内的全套量化版本,已同步上架 Ollama(ornith-1.5:122b)与…

💬 你怎么看?欢迎在评论区讨论。

#Ornith #SWE-bench Pro #Coding Agent
0 Comments

💬 Discussion (0)

Sign in to comment
No comments yet. Be the first to share your thoughts!