Skip to content
localmodel.run

Speech to text · whisper

Can I run Whisper small? Pick your device.

Whisper small is a 244M Speech to text. Realistic peak is ~0.85 GB of memory at fp16 (whisper.cpp). It runs on CPU, so most machines can run it; pick your hardware below.

Memory is a sourced peak-usage anchor at fp16 (whisper.cpp), validated 2026-06-15. See methodology.