Ornith 1.5 122B is an open weight mixture of experts reasoning model from Ornith for coding and agentic work, built for single 80GB GPU serving. About 125B parameters in the BF16 checkpoint · Qwen3.5 MoE layout with 48 layers and 256 experts, 8 active per token · 262,144 token context, roughly 1M with YaRN factor 4 · thinking on by default · trained with Ornith's self improvement loop on top of Qwen3.5 and Gemma 4 derived bases. Weights on Hugging Face under MIT with FP8, NVFP4, GGUF and MLX builds published 2026-10-20.
No benchmark data available yet.
- Typetext
- Context262K tokens (~131 books)
- ReleasedOct 2026
- LicenseOpen Source
- StatusActive
Frequently Asked Questions
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteJais 3 0.9B · MBZUAIGemma 3 12B (free) · Google DeepMindBenchmarks
Key facts · as of 2026-10-21
- Ornith 1.5 122B by Ornith. Not enough public benchmark scores to rank yet.
- List price n/a input · n/a output per 1M tokens (as of 2026-10-21).
How to cite · data as of 2026-10-21
Ornith 1.5 122B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-21. https://benchgecko.ai/model/ornith-1-5-122b
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP