whisper-base vs granite-speech-4.1-2b

Specs, VRAM requirements and download trends — updated 28 July 2026.

openai · A
Params
70 M
Context
30d
4.8 M
apache-2.0 · commercial OK
ibm-granite · B
Params
2.3 B
Context
30d
415 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification whisper-base granite-speech-4.1-2b
Parameters 70 M 2.3 B
Architecture WhisperForConditionalGeneration GraniteSpeechForConditionalGeneration
Context length
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 99 7
Downloads 30d 4,759,784 415,201
Downloads all time 46.7 M 1.6 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2022-09-26 2026-04-16

Download trend

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

6.4 M415 K
whisper-base granite-speech-4.1-2b

VRAM side by side

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

whisper-base · fp16 0.8 GB / 24 GB
✅ Runs comfortably
granite-speech-4.1-2b · fp16 6.2 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons