Which small local LLM cleans up dictation best on Apple Silicon?
We benchmarked four Gemma 4 checkpoints on an M4 Max for dictation cleanup: real latency, memory, and the prompt bug hiding underneath.
Saydrop
Notes on running local AI models on Apple Silicon, native macOS development, and building privacy-first dictation.
Subscribe via RSSWe benchmarked four Gemma 4 checkpoints on an M4 Max for dictation cleanup: real latency, memory, and the prompt bug hiding underneath.
Benchmarks of 18 local cleanup LLMs and five Whisper models on Apple Silicon, comparing latency, accuracy, failures, and the models that won.
Apple Dictation (macOS 26) is now fast, accurate, and free. The real gaps: no AI text cleanup and less convenient hotkey UX.
A deep dive into why we chose Apple's MLX framework for Saydrop, and how we keep Whisper resident in unified memory for sub-second push-to-talk dictation.
Compare local Gemma cleanup, push-to-talk UX, and pricing. Saydrop CHF 39 one-time vs Superwhisper Pro $8.49/mo.
Local speech-to-text on Mac keeps audio private. Compare accuracy, cost, latency, and privacy tradeoffs between on-device and cloud dictation.
Compare local Gemma cleanup vs cloud editing. Saydrop CHF 39 one-time, one-tap workflow. Wispr Flow Pro $144/yr, cross-platform.
Compare 8 macOS dictation apps by cleanup quality, UX, and price. From free Apple Dictation to Saydrop's local Gemma cleanup—find the best fit.