# Ornith-ai/Ornith-1.5-122B (Qwen finetune)

Digest AI · Generative AI & Models · published 2026-10-20T14:19:07Z · updated 2026-10-20T14:39:52Z

Canonical: https://digestai.news/story/ornith-ai-ornith-1-5-122b-qwen-finetune

## Summary

Benchmarks such as Terminal‑Bench, SWE‑Bench, NL2Repo, and ClawEval show state‑of‑the‑art results among open‑source models of comparable size, with faster inference and shorter outputs.

The release includes open weights under an MIT license and detailed server recipes for vLLM and SGLang, exposing an OpenAI‑compatible endpoint with tool‑calling support. Users can interact via standard SDKs or curl, and the model is optimized for terminal‑based coding agents, enabling large‑codebase understanding and automation. A GGUF build is available for local inference, and the team provides configuration tips for extending the context window. Downloads in the last month total 32.

## Key points

- It supports a 262,144‑token context window, extendable to ~1M tokens with YaRN scaling factor 4.0
- Open weights are released under the MIT license with vLLM and SGLang server recipes

## Why it matters

A high‑capacity, open‑source LLM that runs on a single GPU lowers entry barriers for developers and enterprises, accelerating local AI deployment and reducing reliance on costly cloud services.

## Sources

1. [ornith-ai/Ornith-1.5-122B (Qwen finetune)](https://huggingface.co/ornith-ai/Ornith-1.5-122B) (huggingface.co, 2026-10-20, primary source)
2. [Unsloth just released Ornith-1.5-122B GGUFs](https://huggingface.co/unsloth/Ornith-1.5-122B-GGUF) (huggingface.co, 2026-10-20, primary source)

## Cite

Digest AI, "Ornith-ai/Ornith-1.5-122B (Qwen finetune)", 20 October 2026, https://digestai.news/story/ornith-ai-ornith-1-5-122b-qwen-finetune

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/ornith-ai-ornith-1-5-122b-qwen-finetune.json