Use-case guide · Embeddings

Should you pick V100 32GB for embeddings?

V100 32GB has 32 GB VRAM. Whether it's the right fit for embeddings depends on your model size, expected QPS, and budget. Below is what we're seeing in production.

VRAM + model fit

V100 32GB fits models up to ~22B parameters in BF16 comfortably with room for KV-cache. For embeddings specifically, you'll want to leave headroom for context length growth.

Pricing

Live pricing across all providers for V100 32GB is on the GPU detail page — click through for the sortable list.

Throughput

On embeddings workloads, V100 32GB 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.