Can GB200 NVL72 run Whisper Large v3 Turbo?

Yes, the GB200 NVL72 has 13824GB VRAM and Whisper Large v3 Turbo requires approximately 0.4GB VRAM for Q4 quantization. Estimated inference speed: 6281 tokens/second.

✅ — GB200 NVL72 Can Run Whisper Large v3 Turbo

The GB200 NVL72 packs 13824GB VRAM. Whisper Large v3 Turbo needs ~0.4GB. You're good to go.

✅ Plenty of headroom

Hardware Specs

GPU: GB200 NVL72
VRAM: 13824 GB
Bandwidth: 3350 GB/s
MSRP: $0

Model Requirements

Model: Whisper Large v3 Turbo
Parameters: 0.8B
VRAM (Q4): ~0.4 GB
Context: 4,096

Estimated Performance

6281 tok/s

Estimated inference speed (Q4 quantization)

Whisper Large v3 Turbo Details GB200 NVL72 Specs

Try Whisper Large v3 Turbo on a different GPU

Try another model on GB200 NVL72

Full compatibility matrix

✅ — GB200 NVL72 Can Run Whisper Large v3 Turbo

Hardware Specs

Model Requirements

Estimated Performance

Try Whisper Large v3 Turbo on a different GPU

Try another model on GB200 NVL72

Related Checks

More tools

VRAM Calculator

Cloud GPU Pricing

GPU Comparison

Compatibility Lab

✅ — GB200 NVL72 Can Run Whisper Large v3 Turbo

Hardware Specs

Model Requirements

Estimated Performance

Try Whisper Large v3 Turbo on a different GPU

Try another model on GB200 NVL72

Related Checks

More tools

VRAM Calculator

Cloud GPU Pricing

GPU Comparison

Compatibility Lab