Which GPU runs which model · Whisper
Which GPU runs Whisper large-v3, and what it costs per hour
Whisper large-v3 (1.5B) runs in FP16 in about 3 GB of VRAM; no quantisation is needed. Every card on cloudgpu.app has room for it, so the question is only price and speed. The table lists the cards by VRAM class with the price you will actually be billed, read on 2026-09-15.
Recommended card: RTX 3090 24G (24 GB) at $0.21 per hour, the lowest-priced card in a VRAM class that fits.
| VRAM | Cards | Price per hour | Fit |
|---|---|---|---|
| 24 GB | RTX 3090 24G · RTX 4090D 24G · RTX 4090 24G | $0.21 – $0.33/h | Fits fits many times over; the cheapest card is the right one |
| 32 GB | RTX 5090 32G | $0.59/h | Fits fits |
| 48 GB | RTX A6000 48G · RTX 4090 48G | $0.44 – $0.65/h | Fits fits |
| 80 GB | A800 80G · A100 80G | $1.09 – $1.49/h | Fits fits |
| 96 GB | H20 96G · RTX PRO 6000 96G | $1.29 – $1.49/h | Fits fits |
Prices are the retail rates on cloudgpu.app read 2026-09-15 and equal what the billing system charges; VRAM figures were checked on 2026-09-08. Stock changes during the day.
Reading the table
"Fits" here is not in doubt: the FP16 weights take about 3 GB on any card in the table. The note under each verdict says what the extra VRAM buys you.
Data-centre cards (80 GB and 96 GB) are not cheap on cloudgpu.app. If the model fits on a consumer card, the consumer card is the better deal. The prices here are the same numbers the billing system charges.
Questions about running Whisper large-v3
How much VRAM does Whisper large-v3 need?
Whisper large-v3 has 1.5B parameters and runs in FP16 in about 3 GB of VRAM. No quantisation is needed; any card in the table has room to spare, so pick the cheapest one that is in stock.
What is the cheapest GPU that runs Whisper large-v3?
On cloudgpu.app the lowest-priced card we recommend for Whisper large-v3 is the RTX 3090 24G with 24 GB at $0.21 per hour (fits many times over; the cheapest card is the right one). Prices read 2026-09-15; the pricing page shows live stock.
Can I run Whisper large-v3 on an RTX 4090 with 24 GB?
Yes. On a 24 GB card: fits many times over; the cheapest card is the right one. An RTX 4090 24 GB is $0.33 per hour on cloudgpu.app; the RTX 3090 24 GB at $0.21 per hour has the same VRAM and is slower but cheaper.
What does it cost per hour to run Whisper large-v3 on cloudgpu.app?
From $0.21 per hour on the RTX 3090 24G, billed per minute. A 20-minute test is about $0.07; one hour is pre-authorised when the instance starts and unused minutes are refunded on stop. Cards in higher VRAM classes cost more; the table above lists each.
How do I start Whisper large-v3 on a rented GPU?
Open Rent a GPU, choose the JupyterLab template and a card from the table above. The instance is ready in about 100 seconds with a public HTTPS endpoint, and the template already includes Whisper large-v3.
Do I need a credit card or a Chinese account?
No Chinese account, phone number or ID is required. You can pay by card (Visa or Mastercard, any amount from $5) or USDT (TRC-20). A first top-up of $10 or more gets a $5 bonus, so a $10 card payment starts you with $15 of GPU time.