Ornith 1.5

Runs on your device

DeepReinforce · Aug 2026 · Built on Qwen 3.5

DeepReinforce's agentic coding model, self-improved with RL - 1.5 extends the loop to generating its own training tasks. State-of-the-art among open coders at its size, purpose-built for terminal coding agents and tool use. The 9B runs on modest machines; the 35B is a mixture-of-experts (3B active per token) that runs fast for its size and adds vision.

Context
256K tokens
Smallest download
5.6 GB
Runs from
16 GB RAM
License
MIT
codingagenticreasoningMLX for Apple Silicon

Will Ornith 1.5 run on your machine?

This is the same sizing the app uses - not a marketing estimate.

9B5.6 GB downloadRuns fully on your graphics card
35B-A3B (MoE)21.7 GB downloadRuns - experts in RAM, the rest on the GPU

Mixture-of-experts: the always-on layers sit on your card, the experts sit in system memory - bigger than your card, still quick.

On Apple Silicon, system memory is also graphics memory - pick "None / integrated / Apple Silicon" and read the bars against your Mac's memory. The app checks your real hardware before every download.

Variants & sizes

VariantDownloadQuantizationNeedsApple Silicon
9B5.6 GBQ4_K_M16 GB RAMMLX · 5.1 GB
35B-A3B (MoE)MoE21.7 GBQ4_K_M32 GB RAMMLX · 19.5 GB

The app picks the right variant for your machine and verifies every download. Model files come straight from their official repositories, pinned to exact revisions.

License

Ornith 1.5 is released under the MIT - read the terms. The weights download to your machine and stay there; Your Own AI adds no accounts, tracking, or lock-in on top.

Frequently asked questions

Can I run Ornith 1.5 offline?
Yes. Ornith 1.5 is a downloadable model: with Your Own AI it runs entirely on your computer, works with no internet connection, and your conversations never leave your device.
What hardware does Ornith 1.5 need?
The smallest variant (9B, a 5.6 GB download) runs on a machine with 16 GB of memory. Larger variants want more memory or a graphics card - the interactive checker on this page grades every variant against your hardware, using the same logic as the app.
Is Ornith 1.5 free to use?
The model weights are released under the MIT license and download at no charge. Your Own AI itself is free and open source for local use.
How much context does Ornith 1.5 support?
256K tokens of context.

Run Ornith 1.5 in two clicks

Download Your Own AI, pick Ornith 1.5, and the app sizes it to your hardware. Private by architecture - no account needed for local use.