Can You Run Whisper large-v3? Every GPU, Tested

A model that doesn't fit doesn't run slowly, it doesn't run. Here's every card from our bench, sorted by measured speed.

Weights: openai/whisper-large-v3

GPUs that run Whisper large-v3 (8)

GPUSpeedVRAMBasis
NVIDIA L40S193.2 x realtime48GB✓ Measured
NVIDIA H100 80GB HBM3181.47 x realtime80GB✓ Measured
NVIDIA H200163.78 x realtime141GB✓ Measured
NVIDIA A100 40GB SXM4102.47 x realtime40GBEst.
NVIDIA A10G86.07 x realtime24GB✓ Measured
NVIDIA A100 80GB SXM473.83 x realtime80GB✓ Measured
NVIDIA L470.11 x realtime24GB✓ Measured
NVIDIA T444.36 x realtime16GB✓ Measured

Quick answers

What is the fastest GPU for Whisper large-v3?

NVIDIA L40S is the fastest card we've measured running Whisper large-v3, at 193.2 x realtime.

What is the cheapest GPU that can run Whisper large-v3?

NVIDIA T4 ($2,299 MSRP) is the cheapest card on our bench that runs Whisper large-v3, at 44.36 x realtime.

← All models · AI GPU rankings · How we benchmark