Ornith 1.5 is a Qwen3.5-family pair: a 9B dense hybrid and a 35B mixture with 3B active per token, both mostly linear-attention layers with full attention every fourth. These are the text towers converted to the CMF container — a single memory-mapped file read by cortiq, a Rust binary with no ML framework under it. GPU via Vulkan/Metal/DX12 with a CPU fallback.

Both 4-bit tiled with ladder scales (q4tp), quantized straight from the bf16 checkpoints, MTP draft head included. The upstream repos are vision-language; these files carry the text tower — image input is not part of the container.

Steady-state decode, cortiq bench --core, single stream, A100 80GB over Vulkan, cortiq 0.5.99. The whole token runs as one submitted graph — linear-attention state, expert routing and the draft head included.

The 9B on the M4 was verified against the published file itself — downloaded back from this repo, checksum matched, generation coherent.

For scale: this stack decodes the same class of files at ~55–65% of an RTX 5090's rate, so consumer-card numbers run higher.

Speaks the OpenAI API, so anything that talks to OpenAI talks to it.

Each .cmf ships a .sha256 beside it.