whisper-large-v3-turbo vs whisperkit-coreml

Specs, VRAM requirements and download trends — updated 10 November 2026.

openai · A · Open weights
Params
810 M
Context
—
30d
5.2 M
mit · commercial OK
argmaxinc · B · Open weights
Params
—
Context
—
30d
51.6 M
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification whisper-large-v3-turbo whisperkit-coreml
Parameters 810 M —
Architecture WhisperForConditionalGeneration —
Context length — —
Licence mit mit
Commercial use Allowed Allowed
Languages 99 —
Downloads 30d 5,175,000 51,550,655
Downloads all time 127.5 M 135.3 M
Quantizations on the Hub SAFETENSORS —
Gated No No
First seen on the Hub 2024-10-01 2024-02-28

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

51.6 M5.2 M
whisper-large-v3-turbo whisperkit-coreml

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

whisper-large-v3-turbo · fp16 2.4 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons