Use-case guide · Summarisation

Should you pick Instinct MI250X for summarisation?

Instinct MI250X has 128 GB VRAM. Whether it's the right fit for summarisation depends on your model size, expected QPS, and budget. Below is what we're seeing in production.

VRAM + model fit

Instinct MI250X fits models up to ~90B parameters in BF16 comfortably with room for KV-cache. For summarisation specifically, you'll want to leave headroom for context length growth.

Pricing

Live pricing across all providers for Instinct MI250X is on the GPU detail page — click through for the sortable list.

Throughput

On summarisation workloads, Instinct MI250X 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.