Speech-to-text Sourced statement

Whisper large-v3-turbo on Mac (Apple Silicon M1–M4)

Benchmark pending. We haven't measured this pair yet. Below is what the sources say about this hardware, quoted with links.

Unified memory shared by CPU and GPU. Runtime support varies a lot (Metal via whisper.cpp/MLX; PyTorch MPS is often partial).

EvidenceSourced statement

Commercial useYes

Licensemit

Stated memory~6 GB VRAM

Device memory16 GB unified memory

Results

Benchmark pending. No measured numbers from us yet for Whisper large-v3-turbo on Apple Silicon. Get notified or send us your numbers (with the method).

What the sources say about Apple Silicon

Third-party docs whisper.cpp: 'Apple Silicon first-class citizen'; on Apple Silicon inference runs fully on the GPU via Metal. source
Model authors OpenAI lists ~6 GB required VRAM for turbo, which fits in 16 GB unified memory. source
Caveat: Memory figure is for the PyTorch implementation

Method

We haven't run this pair. Everything on this page is quoted from the linked sources, with the source type labelled (model authors vs third parties). Vendor numbers are often measured under favourable conditions.

Ways to run Whisper large-v3-turbo

Runtime	Precision	Documented devices
openai-whisper (PyTorch)	fp16/fp32	CPU, CUDA	source
faster-whisper (CTranslate2)	int8, fp16, fp32	CPU, CUDA	source
whisper.cpp (ggml)	fp16, quantized (q5/q8)	CPU (x86/ARM), Apple Metal + Core ML, CUDA, Vulkan, OpenVINO	source
Hugging Face transformers	fp16/fp32	CPU, CUDA	source

Run it

git clone https://github.com/ggml-org/whisper.cpp && cd whisper.cpp
sh ./models/download-ggml-model.sh large-v3-turbo
cmake -B build && cmake --build build -j --config Release   # Metal is used automatically on Apple Silicon
./build/bin/whisper-cli -m models/ggml-large-v3-turbo.bin -f samples/jfk.wav

Copied from the linked README. We haven't run it on this device.

Caveats

Memory figure is for the PyTorch implementation