OpenAI
Whisper Tiny
Fastest Whisper model. Runs on anything including phones. 10x faster than Large.
0.039B parameterswhisperapache-2.01GB - 1GB VRAM
Check Your Hardware
See which quantizations of Whisper Tiny your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| FP16 | 16 | 0.075 GB | 1 GB | 2 GB | 65% |
Frequently Asked Questions
How much VRAM do I need to run Whisper Tiny?
Whisper Tiny requires 1GB VRAM minimum with FP16 quantization. For full precision, you need 1GB VRAM.
What is the best quantization for Whisper Tiny?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.