OwnRig

Whisper Large V3 Turbo on Apple M4 Pro (24GB Unified)

Apple M4 Pro (24GB Unified) runs Whisper Large V3 Turbo excellently at FP16. This is a strong pairing.

Model Size

810M

Device VRAM

24 GB

Bandwidth

273 GB/s

Quantizations Tested

1

Performance by Quantization

Each row shows Whisper Large V3 Turbo performance at a different quality level on Apple M4 Pro (24GB Unified).

QuantizationSpeedTTFTFits in VRAMRatingConfidence
FP16250ms✓ YesExcellentestimated

Notes

FP16

Uses Core ML acceleration for transcription. Real-time capable on Mac.

About Whisper Large V3 Turbo

Whisper Large V3 Turbo (810M) is a transcription model. Distilled version of Whisper Large V3. 8x faster than the full model with minimal quality loss. The go-to for real-time transcription on local hardware. Runs comfortably on any GPU with 2GB+ VRAM.

View all Whisper Large V3 Turbo hardware options →

About Apple M4 Pro (24GB Unified)

Apple M4 Pro (24GB Unified) has 24 GB at 273 GB/s. Available in MacBook Pro 14", MacBook Pro 16", Mac Mini.

See all models Apple M4 Pro (24GB Unified) can run →

Source: MLX performance estimates based on device bandwidth (2026-03-15)

Data last updated: 2026-03-15