whisper-large-v3 vs cohere-transcribe-03-2026

Specs, VRAM requirements and download trends — updated 6 August 2026.

openai · A
Params
1.5 B
Context
30d
5.5 M
apache-2.0 · commercial OK
CohereLabs · B
Params
2.1 B
Context
30d
1.0 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification whisper-large-v3 cohere-transcribe-03-2026
Parameters 1.5 B 2.1 B
Architecture WhisperForConditionalGeneration CohereAsrForConditionalGeneration
Context length
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 99 14
Downloads 30d 5,497,354 1,009,589
Downloads all time 139.4 M 2.8 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No Yes — accept licence
First seen on the Hub 2023-11-07 2026-03-24

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

6.0 M1.0 M
whisper-large-v3 cohere-transcribe-03-2026

VRAM side by side

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

cohere-transcribe-03-2026 · fp16 5.4 GB / 24 GB
✅ Runs comfortably
whisper-large-v3 · fp16 10.9 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons