Open-source Ornith-1.5-122B MoE coding model runs on a desk with 86GB memory
lmoroney · x · 2026-10-22
Ornith released Ornith-1.5-122B, an open MoE model built for coding and agent tasks, developed on top of Qwen3.5 with additional pre/mid/post-training. SGLang shipped day-zero support with reasoning, tool calling, and 262K context; a community recipe runs the 4-bit quant on a DGX Spark in 86GB total memory. The author suggests testing it on real tickets from your own repo before checking leaderboards.
More from coding & agent
- Cua Spaces SDK lets Hermes and other agents run in sandboxes on your own hardware — Teknium · 2026-10-23
- PHP hit by two unauthenticated RCE flaws; ProjectDiscovery launches free internet-wide alert service — cyb3rops · 2026-10-23
- Modal open-sources Spindle, a Tinker-compatible training server that charges GPU time instead of tokens — josh_wills · 2026-10-23
- Testing the Azure Cosmos DB Agent Kit: what it found reviewing a Claude-built app, in RUs saved — adnan_hashmi · 2026-10-23
- Dev ditches endless chat threads for a visual dashboard to manage her AI agents — Salmaaboukarr · 2026-10-23
- Warp cuts coding agent verification bottleneck with per-agent computer-use and clip reviews — vikvang1 · 2026-10-23