Providers & Models
Choose a Whisper model
Smaller is faster but less accurate. base-q8_0 is the default. large-v3-turbo is the top tier on-device.
Open Settings → Models. You see the full list of Whisper variants with size, speed estimate, and download status. The active model is highlighted.
Quantization
Models tagged q8_0 are 8-bit quantized. They give roughly the same accuracy as the full-precision version (2 to 3 % drop) at about half the size and twice the speed. Default everywhere on-device.
Download flow
- Pick a model from the list, click Download.
- Progress bar shows the current MB/MB.
- Once finished, the model becomes active automatically.
- Previous models stay on disk until you click Remove.
Was this helpful?
In this category
Providers & Models
Local mode: offline by default
Dimmy ships with Whisper running on your device. No API key, no internet, no per-minute cost. Works on a plane.
Providers & Models
Cloud providers compared
Groq is fastest, OpenAI is the gold standard, Deepgram leads on streaming. All optional. Bring your own key.
Providers & Models
Add your API key
Open Settings → Providers & keys, find the provider card, paste the key. It is encrypted on your machine. You can update keys at any time.
Providers & Models
Optional on-device LLM
Run the LLM enhancement pass locally via llama.cpp. No cloud, no key, no per-token cost. Pick a model to match your GPU memory.
Last updated: 2026-05-22