Phi models
1 Phi model on Hugging Face, from 7.6B to 7.6B parameters. The cheapest way to run Phi-mini-MoE-instruct is $0.176/hr.
Phi models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Phi-mini-MoE-instruct | 7.6B | BF16 | 17.1 GB | RTX A5000 | $0.176/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
