OpenAI

Whisper Large v3 Turbo

Optimized large Whisper model. Near-best accuracy with faster inference.

0.81B parameterswhispermit1.9GB - 1.9GB VRAM

Check Your Hardware

See which quantizations of Whisper Large v3 Turbo your hardware can run.

Quantization Options

QuantizationBitsFile SizeVRAM NeededRAM NeededQuality
Q8_081.6 GB1.9 GB2.5 GB
95%

Frequently Asked Questions

How much VRAM do I need to run Whisper Large v3 Turbo?

Whisper Large v3 Turbo requires 1.9GB VRAM minimum with Q8_0 quantization. For full precision, you need 1.9GB VRAM.

What is the best quantization for Whisper Large v3 Turbo?

Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.