Developers

Local Models

Language Models (LLM)

For step-by-step setup instructions for LM Studio and Ollama, see the Local LLM Setup guide.

Speech-to-Text (STT)

  • All STT models are stored in ~/Library/Application Support/hyprnote/models/stt/
  • The built-in whisper-cpp backend is now an optional compile-time feature. Production builds on macOS Apple Silicon use the Argmax sidecar by default. Whisper-cpp quantized models have been removed from the settings UI.

Cactus Engine (Beta)

Cactus is a new local STT backend that runs optimized Whisper models. Cactus models are listed in Settings > Transcription under the Hyprnote provider. Models with an "Apple NPU" suffix use the Apple Neural Engine for hardware-accelerated inference on Apple Silicon Macs; non-Apple variants run on any platform.

ModelQuantizationPlatform
Whisper Small (INT4)INT4General
Whisper Small (INT8)INT8General
Whisper Small (INT8, Apple NPU)INT8Apple Silicon
Whisper Medium (INT4)INT4General
Whisper Medium (INT4, Apple NPU)INT4Apple Silicon
Whisper Medium (INT8)INT8General
Whisper Medium (INT8, Apple NPU)INT8Apple Silicon

Cactus models are downloaded and managed from the Settings UI. They are stored in a separate cactus/ directory within the models folder.

Argmax Models

Manual download:

For details on how your data is handled when using local vs cloud models, see AI Models & Data Privacy.

If you have Huggingface CLI installed:

hf download argmaxinc/whisperkit-pro \
  --include "openai_whisper-large-v3-v20240930_626MB/*" \
  --local-dir "$HOME/Library/Application Support/hyprnote/models/stt"