Loading…
Loading…
Models / Phi-3.5-MoE
1 model (~41.9B) · ↓ 93.2K downloads a month · from $1.16/h on 2x Nvidia A100 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-3.5-MoE-instruct | vLLM | 84 GB | 96.5 GB | $1.16/h 2x Nvidia A100 |
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").