OpenAI
Whisper Small
Fast transcription for resource-limited devices. 4x faster than Large.
0.24B parameterswhisperapache-2.02GB - 2GB VRAM
Check Your Hardware
See which quantizations of Whisper Small your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| FP16 | 16 | 0.46 GB | 2 GB | 4 GB | 82% |
Frequently Asked Questions
How much VRAM do I need to run Whisper Small?
Whisper Small requires 2GB VRAM minimum with FP16 quantization. For full precision, you need 2GB VRAM.
What is the best quantization for Whisper Small?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.