Loading…
Loading…
Models / Phi-3-mini-4k
2 models (~3.82B) · ↓ 360K 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 |
|---|---|---|---|---|
| Originalmicrosoft/Phi-3-mini-4k-instruct | vLLM | 7.6 GB | 12.5 GB | $0.14/h RTX A4000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalmicrosoft/Phi-3-mini-4k-instruct-onnx | ONNX Runtime GenAI | 2.1 GB | 5.6 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").