Fact · Dictation in your apps
2GB of VRAM
The Whisper README gives about 2 GB of required VRAM for the small model.
Checked against its source on October 17, 2026
In the source's own words
“base 74 M base.en base ~1 GB ~7x small 244 M small.en small ~2 GB ~4x”
openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision, OpenAI, GitHub (OpenAI repository), 2023, Available models and languages table.
Open the original- What it measures
- The small model has 244 million parameters, the next size up from base in the same table.
- What it does not show
- Approximate table value. Real usage depends on the model format and the tool that loads it.