Updated November 2026

Whisper benchmarks on Windows.

Whisper speed on CPU and GPU, from public tests.

What to pick

With a graphics card

Large v3 Turbo. It is close to Large v3 in accuracy and 2 to 3 times faster.

Without a graphics card

Base or Small for dictation. Large models can take more than 10 times the audio length on a CPU.

Short on disk space

A Q8 or Q5 version. The file is much smaller and accuracy barely changes.

CPU vs GPU

11-second clip · Core i9-13980HX, RTX 4090 Laptop.

ModelCPUGPU · VulkanGPU · CUDA
Tiny1.98 s0.31 s0.32 s
Base4.54 s0.42 s0.41 s
Small20.4 s0.82 s0.84 s
Medium73.6 s2.02 s1.91 s
Large v3133.5 s3.73 s3.90 s

Source: StarWhisper, July 2026

Turbo vs Large v3

Speed versus audio length. Higher is faster.

TestLarge v3Large v3 Turbo
RTX 4070 Ti · whisper.cpp15× real time40× real time
NVIDIA A100 · OpenAI1× (reference)About 8×

Source: x2q, June 2026 · OpenAI Whisper

Integrated graphics

Large v3 Turbo Q8 · Ryzen 7 PRO 4750U laptop.

ClipCPUGPU · Vulkan
11 seconds9.85 s4.40 s
35 seconds20.36 s9.59 s

Source: transcribe.cpp, September 2026

Smaller files, same accuracy

Large v3 Turbo on LibriSpeech. Lower is better.

VersionWord error rate
Full (F16)2.01%
Q82.01%
Q62.01%
Q5_K_M2.03%
Q42.04%

Source: transcribe.cpp, September 2026

Whisper benchmarks FAQ

Do I need a graphics card to run Whisper?

No. Base and Small run on a recent processor. A graphics card makes large models much faster: 36 times faster in one test with Large v3.

Is Vulkan as fast as CUDA for Whisper?

On NVIDIA cards, yes. In the same test, Vulkan and CUDA stayed within a few percent of each other. Vulkan also works on AMD and Intel graphics.

Which Whisper model is the fastest?

Tiny and Base are the fastest. Among the accurate models, Large v3 Turbo is much faster than Large v3.

Do quantized Whisper models lose accuracy?

Very little. On clean English speech, the error rate went from 2.01% for the full version to 2.04% for the smallest one.