Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding
Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.
Ornith-1.0 ships MIT-licensed open weights in 9B, 31B, 35B MoE, and 397B MoE variants, with the tested 35B Q4_K_M GGUF fitting in 20GB and running agentic coding workflows locally. The practical takeaway is that open-weight local coding agents are now credible for multi-tool repository navigation and code-search tasks, not just single-shot completion, giving teams a deployable alternative when they need control over weights, licensing, and data locality.
A new MIT-licensed open-weights model family (9B/31B dense, 35B/397B MoE) built on Gemma 4 and Qwen 3.5 hits SOTA among comparable open-source models on coding, and the 35B Q4 quant runs locally in ~20GB at 103 tok/s while handling multi-step agentic tool calls reliably. This means you can run a competent self-scaffolding coding agent on a single workstation GPU under a permissive license—no API costs, no per-token billing, and no rate limits for your harness.