A friendly local chat app for the Orchid model — download, open, and start talking. The model runs entirely on your machine, so nothing leaves your computer.
⚛ Builds are in final packaging — links go live with the public release. macOS is on the roadmap.
[ Orchid Desktop — app screenshot ]No account, no cloud, no data leaving your device. Works offline.
Bundles the ternative engine — runs on hardware you already own.
Free for personal and commercial use. Weights and engine are public.
Grab the raw weights and run them through the engine directly. You'll need both Orchid model files and a ternative build.
Model · weights
The I2_S base GGUF (~1.1 GB) plus the aligned LoRA adapter (~90 MB), hosted on Hugging Face.
huggingface-cli download MicheRomChis/orchid-1.0 \
ggml-model-i2_s.gguf dpo_aligned-lora.gguf \
--local-dir ./orchid-models
Clone and build the C++17 / CUDA engine, then point it at the weights. Windows & Linux.
git clone --depth 1 \ https://github.com/michelangeloromerochisco/ternative cmake -B build -DCMAKE_BUILD_TYPE=Release \ && cmake --build build --parallel
Orchid was built to run on consumer hardware. No discrete GPU is required — CPU-only mode runs at ~6 tok/s.
| Minimum | Recommended | |
|---|---|---|
| GPU VRAM | 0 (CPU) | 4 GB |
| RAM | 8 GB | 16 GB |
| Storage | 1.3 GB | 2 GB |
| OS | Win / Linux | — |