Fact · Dictation in your apps
5GB of VRAM
The Whisper README gives about 5 GB of required VRAM for the medium model.
Checked against its source on October 17, 2026
In the source's own words
“medium 769 M medium.en medium ~5 GB ~2x large 1550 M N/A large ~10 GB 1x”
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 medium model sits between small and large in the table, both in memory and in speed.
- What it does not show
- Approximate table value, for GPU memory only.
Source
Cited on
- Is Whisper AI Safe? Privacy and Security ExplainedGuide
- How to Run Whisper Locally on Your Own ComputerGuide
- Speech to Text on Linux: Dictation on Ubuntu and MintGuide
- Transcribe Audio With Whisper, ChatGPT or GeminiGuide
- What is the best GPU for Whisper?Question
- Which Whisper model should I use?Question