Ornith-1.5-35B-A3B

· llama.cpp · 256K context · RTX 5070 · 12 GB

Ornith 1.5, a 35B mixture-of-experts with built-in MTP.

32 tok/sdecode

818 tok/sprefill

256Kcontext window

Tested on this cardOct 8, 2026

Run it

Follow the steps below to download and run this recipe. Omarchy Local AI lists the recipes it can launch on your hardware. The server then answers on http://localhost:8000/v1.

1 Download the weights

hf download ornith-ai/Ornith-1.5-35B-A3B-GGUF Ornith-1.5-35B-Q4_K_M.gguf mmproj-Ornith-1.5-35B-BF16.gguf \
  --revision 12393612fd4f730ff5aadc23e9b8f9648aa49ceb \
  --local-dir ~/models/Ornith-1.5-35B-A3B-GGUF-12393612

2 Start the server

docker run --rm \
  --gpus all \
  -p 8000:8080 \
  --shm-size 16g \
  -e CUDA_DEVICE_ORDER=PCI_BUS_ID \
  -v ~/models/Ornith-1.5-35B-A3B-GGUF-12393612:/models:ro \
  --entrypoint /app/llama-server \
  ghcr.io/ggml-org/llama.cpp:server-cuda12-b11146@sha256:52192a23c7b258044463aebba78826cdff39a7393b713edc313324b343a7b836 \
  --model /models/Ornith-1.5-35B-Q4_K_M.gguf \
  --cache-type-k q8_0 \
  --cache-type-v q8_0 \
  --load-mode none \
  --host 0.0.0.0 \
  --port 8080 \
  --ctx-size 262144 \
  --fit-target 2560 \
  --flash-attn on \
  --parallel 1 \
  --jinja \
  --mmproj /models/mmproj-Ornith-1.5-35B-BF16.gguf \
  --cache-ram 0 \
  --metrics \
  --spec-type draft-mtp \
  --spec-draft-n-max 3 \
  --temp 0.6 \
  --top-p 0.95 \
  --top-k 20 \
  --min-p 0.0

What it passed

✓ loadLoads and serves within an hour

✓ chatAnswers a plain question and stops on its own

✓ reasoningThinks separately and gets 17 × 23 right

✓ toolsCalls a tool with the right arguments and uses the result

✓ contextRecalls a code buried in a prompt that fills 85% of the window

✓ speedDecodes at 15 tok/s or more

Passed all six checks on a real RTX 5070 on Oct 8, 2026.

Details

Weights: ornith-ai/Ornith-1.5-35B-A3B-GGUF @ 12393612fd ›
Image: ghcr.io/ggml-org/llama.cpp:server-cuda12-b11146@sha256:52192a23c7b258044463aebba78826cdff39a7393b713edc313324b343a7b836
Launch: llama.cpp-ornith-1.5-35b-a3b-q4-k-m-mtp-autofit-256k-rtx-5070-12gb ›
Recipe file: registry/recipes/nvidia/rtx-5070-12gb/ornith-1.5-35b-a3b.llama.cpp.256k.json ›
Model released: Aug 18, 2026
Tested: owner, RTX 5070