Use-case guide · Information extraction

Should you pick Gaudi 2 for information extraction?

Gaudi 2 has 96 GB VRAM. Whether it's the right fit for information extraction depends on your model size, expected QPS, and budget. Below is what we're seeing in production.

VRAM + model fit

Gaudi 2 fits models up to ~67B parameters in BF16 comfortably with room for KV-cache. For information extraction specifically, you'll want to leave headroom for context length growth.

Pricing

Live pricing across all providers for Gaudi 2 is on the GPU detail page — click through for the sortable list.

Throughput

On information extraction workloads, Gaudi 2 typically delivers the throughput published in its FP16 spec, minus the framework overhead (vLLM ≈ 85% MFU, TGI ≈ 70%).

Try the calculator to size the hardware for your specific model, or see all GPUs on the InferenceScore leaderboard.