# Can I run Whisper small on Nvidia GeForce RTX 4060 Ti (16GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at fp16 (whisper.cpp) using ~0.85 GB of ~15 GB usable.

- Model: 244M Speech to text, peak ~0.85 GB memory at fp16 (whisper.cpp)
- Device: 16 GB vram, ~15 GB usable
- Tools: whisper.cpp, faster-whisper, MacWhisper
- License: MIT (commercial use: yes)

Sources: https://github.com/openai/whisper, https://github.com/ggml-org/whisper.cpp.

More: https://localmodel.run/can-i-run/whisper-small/nvidia-rtx-4060-ti-16gb