Loading…
Loading…
Models / distilgpt2
1 model (~88M) · ↓ 1.8M downloads a month · from $0.08/h on GTX 1660 SUPER 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 |
|---|---|---|---|---|
| Originaldistilbert/distilgpt2 | vLLM | 180 MB | 2.4 GB | $0.10/h RTX 3060 |
| Main (Xenova)Xenova/distilgpt2 | ONNX Runtime | 80 MB | 1.1 GB | $0.08/h GTX 1660 SUPER |
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").