Skip to content
localmodel.run

audio model · whisper · macOS

Can I run Whisper large-v3 on Apple M5 Pro (48GB)?

Compatibility verdict memory check
Yes, it runsmoderate speed

Yes. Whisper large-v3 runs on Apple M5 Pro (48GB) at int8 (~2.5 GB of ~32 GB usable).

Needs ~2.5 GB Device usable ~32 GB

Runs at int8 using ~2.5 GB of ~32 GB usable.

Peak memory
~2.5 GB
Usable on device
~32 GB
Device memory
48 GB
Quant
int8

How to run it

Use whisper.cpp or faster-whisper at int8. It is light enough to run on CPU; a GPU just makes it faster.

Model whisper
Type
Speech to text
Parameters
1.55B
Peak memory
~2.5 GB at int8
License
MIT
Full Whisper large-v3 requirements →
Device macOS
Memory
48 GB unified
Usable for weights
~32 GB
Best runtime
MLX direct / Ollama (MLX backend)
Best models for Apple M5 Pro (48GB) →

You could also run

Run Whisper large-v3 on other hardware

FAQ

Can Apple M5 Pro (48GB) run Whisper large-v3?

Yes. Whisper large-v3 runs on Apple M5 Pro (48GB) at int8 (~2.5 GB of ~32 GB usable).

How much memory does Whisper large-v3 need?

Apple M5 Pro (48GB) has room to spare. At int8 the realistic peak is ~2.5 GB of memory.

What do I use to run Whisper large-v3 locally?

Whisper large-v3 runs in whisper.cpp or faster-whisper (among others). It runs on CPU, so no GPU is required.

Sources

VRAM figures are sourced peak-usage anchors at the noted quant, validated 2026-06-15. See methodology.