Which GPU runs which model · FLUX
Which GPU runs FLUX.1 dev, and what it costs per hour
FLUX.1 dev (12B + T5-XXL encoder) takes about 24 GB of VRAM as FP16 weights and about 12 to 16 GB at FP8, before the KV cache for your context window. The table lists the cards on cloudgpu.app by VRAM class, whether the model fits, and 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 FP8 fits; FP16 is tight |
| 32 GB | RTX 5090 32G | $0.59/h | Fits FP16 fits: the recommended card |
| 48 GB | RTX A6000 48G · RTX 4090 48G | $0.44 – $0.65/h | Fits FP16 fits |
| 80 GB | A800 80G · A100 80G | $1.09 – $1.49/h | Fits FP16 with batch generation |
| 96 GB | H20 96G · RTX PRO 6000 96G | $1.29 – $1.49/h | Fits FP16 with batch generation |
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" is judged for the FP8 weights plus a working context window; FP16 needs roughly twice the VRAM. The note under each verdict says how much context you get.
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 FLUX.1 dev
How much VRAM does FLUX.1 dev need?
FLUX.1 dev has 12B + T5-XXL encoder parameters. The FP16 weights take about 24 GB; at FP8 the weights take about 12 to 16 GB. Leave a few GB for the text encoders, the VAE and activations, more if you generate in batches or at high resolution.
What is the cheapest GPU that runs FLUX.1 dev?
On cloudgpu.app the lowest-priced card we recommend for FLUX.1 dev is the RTX 3090 24G with 24 GB at $0.21 per hour (FP8 fits; FP16 is tight). Prices read 2026-09-15; the pricing page shows live stock.
Can I run FLUX.1 dev on an RTX 4090 with 24 GB?
Yes. On a 24 GB card: FP8 fits; FP16 is tight. 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 FLUX.1 dev 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 FLUX.1 dev on a rented GPU?
Open Rent a GPU, choose the FLUX.1 dev (ComfyUI) 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 FLUX.1 dev.
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.