Use-case guide · Speech-to-text

Should you pick L4 for speech-to-text?

L4 has 24 GB VRAM. Whether it's the right fit for speech-to-text depends on your model size, expected QPS, and budget. Below is what we're seeing in production.

VRAM + model fit

L4 fits models up to ~17B parameters in BF16 comfortably with room for KV-cache. For speech-to-text specifically, you'll want to leave headroom for context length growth.

Pricing

Live pricing across all providers for L4 is on the GPU detail page — click through for the sortable list.

Throughput

On speech-to-text workloads, L4 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.