Whisper · MIT
Distilled version of Whisper Large V3. 8x faster than the full model with minimal quality loss. The go-to for real-time transcription on local hardware. Runs comfortably on any GPU with 2GB+ VRAM.
Whisper Large V3 Turbo (810M) requires 1.6 GB VRAM at recommended quality (FP16). For the best experience, Starter AI Desktop ($582) is recommended.
— OwnRig methodology, data updated 2026-03-15
| Quality | Quantization | VRAM | File Size |
|---|---|---|---|
| full | FP16 | 1.6 GB | 1.5 GB |
Performance data for Whisper Large V3 Turbo across different hardware.
| Device | Quantization | Speed | Rating | Fits in VRAM |
|---|---|---|---|---|
| NVIDIA GeForce RTX 3060 12GB | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 4060 Ti 16GB | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 4070 Ti Super | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 4070 Super | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 4080 Super | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 4090 | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 3090 | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 5080 | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 5090 | FP16 | — | Excellent | ✓ |
| Apple M4 Pro (24GB Unified) | FP16 | — | Excellent | ✓ |
| Apple M4 Pro (48GB) | FP16 | — | Excellent | ✓ |
| Apple M4 Max (36GB Unified) | FP16 | — | Excellent | ✓ |
| Apple M4 Max (64GB Unified) | FP16 | — | Excellent | ✓ |
| Apple M4 Max (128GB Unified) | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 4060 8GB | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 4070 Ti 12GB | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 3080 10GB | FP16 | — | Excellent | ✓ |
| Apple M3 Pro (18GB Unified) | FP16 | — | Good | ✓ |
Data confidence: estimated. Last updated: 2026-03-15. Source