OpenAI
Whisper Turbo
8x faster than Large with minimal quality loss. Best speed/accuracy trade-off.
0.81B parameterswhisperapache-2.06GB - 6GB VRAM
Check Your Hardware
See which quantizations of Whisper Turbo your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| FP16 | 16 | 1.6 GB | 6 GB | 8 GB | 95% |
Frequently Asked Questions
How much VRAM do I need to run Whisper Turbo?
Whisper Turbo requires 6GB VRAM minimum with FP16 quantization. For full precision, you need 6GB VRAM.
What is the best quantization for Whisper Turbo?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.