whisper-large-v3-turbo vs whisper-medium

Specs, VRAM requirements and download trends — updated 27 August 2026.

openai · A

Params

810 M

Context

—

30d

6.7 M

mit · commercial OK

openai · B

Params

760 M

Context

—

30d

378 K

apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	whisper-large-v3-turbo	whisper-medium
Parameters	810 M	760 M
Architecture	WhisperForConditionalGeneration	WhisperForConditionalGeneration
Context length	—	—
Licence	mit	apache-2.0
Commercial use	Allowed	Allowed
Languages	99	99
Downloads 30d	6,703,764	378,075
Downloads all time	117.9 M	20.0 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2024-10-01	2022-09-26

Daily snapshots, last 56 days (28 Jul – 21 Sep)

8.7 M342 K

whisper-large-v3-turbo whisper-medium

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

whisper-large-v3-turbo · fp16 2.4 GB / 24 GB

✅ Runs comfortably

whisper-medium · fp16 4.0 GB / 24 GB

✅ Runs comfortably