Loading…
Loading…
Models / whisper-small.en
GPU memory needed (smallest version of each): whisper-small.en ~242M about 1.1 GB. The cheapest runs on Quadro P4000 from $0.07/h right now.
1 model (~242M) · ↓ 169.8K downloads a month · from $0.07/h on Quadro P4000 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalopenai/whisper-small.en | vLLM | 480 MB | 2.6 GB | $0.09/h RTX 3060 |
| timestamped (onnx-community)onnx-community/whisper-small.en_timestamped | ONNX Runtime | 60 MB | 1.1 GB | $0.07/h Quadro P4000 |
| Main (Xenova)Xenova/whisper-small.en | ONNX Runtime | 50 MB | 1.1 GB | $0.07/h Quadro P4000 |
| Main (onnx-community)onnx-community/whisper-small.en | ONNX Runtime | 60 MB | 1.1 GB | $0.07/h Quadro P4000 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").