AI Agent StoreOrnith · Download verified
Ornith 1.5 122B
Run a large reasoning model yourself for coding and tool-assisted work. Choose the weight format to fit your hardware before planning a deployment.
First reviewed 2026-10-21 · Checked 2026-11-03. The launch date has not been confirmed.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Try it on your hardware and tasks before relying on it.
What you can use today
You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.
Exact download ID: ornith-ai/Ornith-1.5-122B. Thinking is enabled by default; the serving guide supports tool calls. No adjustable effort menu or independently matched result is verified here.
The publisher labels the weights MIT. Roughly 250 GB of raw BF16 weights require suitable hardware before runtime memory; compressed formats need their own evaluation. Use the exact runtime and weight format when comparing memory requirements.
The documented standard window is 262,144 tokens. Extending it toward one million requires explicit scaling and can reduce quality on shorter inputs.
A download, with no verified hosted token price. Publisher evaluations do not establish an independent ranking.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.
Compare caching and long-context costs ↗