● Google Research • FLAN-T5 (Base) • Live on Runtide

Google Open-Source AI Inference

This model is running 100% on CPU inside a Runtide MicroVM container on your winshowpauly10@gmail.com account. No GPU required.

TRY A PROMPT:
Why MicroVMs boot fast
Translate to ES & DE
Why CPU Quantization
2-sentence product pitch
Provider: Google Open Source • Port 8080
Model Response:
Latency: - Hardware: CPU (AVX-512) Model: google/flan-t5-base GPU Cost: $0.00