Loading…
Loading…
Models / Phi-3-mini-128k
2 models (~3.82B) · ↓ 211.7K downloads a month · from $0.09/h on Titan Xp 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-128k-instruct | vLLM | 7.6 GB | 14.3 GB | $0.16/h RTX 4060 Ti |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalmicrosoft/Phi-3-mini-128k-instruct-onnx | ONNX Runtime GenAI | 2.2 GB | 7.2 GB | $0.09/h Titan Xp |
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").