Skip to content
localmodel.run

Speech to text · whisper

Can I run Whisper large-v3-turbo? Pick your device.

Whisper large-v3-turbo is a 809M Speech to text. Realistic peak is ~1.5 GB of memory at int8. It runs on CPU, so most machines can run it; pick your hardware below.

Memory is a sourced peak-usage anchor at int8, validated 2026-06-15. See methodology.