whisper-large-v3 vs faster-whisper-small

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

openai · A · Open weights
Params
1.5 B
Context
—
30d
3.5 M
apache-2.0 · commercial OK
Systran · B · Open weights
Params
—
Context
—
30d
5.7 M
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification whisper-large-v3 faster-whisper-small
Parameters 1.5 B —
Architecture WhisperForConditionalGeneration —
Context length — —
Licence apache-2.0 mit
Commercial use Allowed Allowed
Languages 99 99
Downloads 30d 3,515,562 5,718,052
Downloads all time 153.2 M 26.0 M
Quantizations on the Hub SAFETENSORS —
Gated No No
First seen on the Hub 2023-11-07 2023-11-23

Download trend

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

5.7 M1.8 M
whisper-large-v3 faster-whisper-small

VRAM side by side

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

whisper-large-v3 · fp16 10.9 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons