GPUs for image generation
As of — SDXL at 16-bit: from $0.15 per GPU-hour on the NVIDIA RTX A4000 (Hyperstack), 50 cards qualify; FLUX.1 [dev] at 16-bit: from $0.16 per GPU-hour on the NVIDIA V100 32GB (Geodd), 31 cards qualify. Rates are each card’s cheapest live on-demand rate card across the providers we track, read hourly, every one linked to the page it was read from.
An image model also keeps its weights in GPU memory at 2 bytes per parameter in 16-bit, and its text encoders and the decoder come on top. The parameter counts below are the models’ own.
SDXL at 16-bit
2.6 billion UNet parameters × 2 bytes = 5.2 GB, plus two text encoders and the decoder: a card with 12 GB or more.
| Card, memory | Cheapest on-demand | Provider, read | Median rate card | $ per GB-hour | Deploy |
|---|---|---|---|---|---|
| NVIDIA RTX A4000 · 16 GB | $0.15 |  Hyperstackcaptured | $0.25 11 providers | $0.009 | Deploy ↗ |
| NVIDIA V100 32GB · 32 GB | $0.16 |  Geoddcaptured | $1.15 11 providers | $0.005 | Deploy ↗ |
| NVIDIA GeForce RTX 3090 · 24 GB | $0.18 |  OpenRelaycaptured | $0.42 10 providers | $0.007 | Deploy ↗ |
| NVIDIA A2 · 16 GB | $0.20 | Infomaniak captured | $0.23 2 providers | $0.012 | Deploy ↗ |
| NVIDIA A30 · 24 GB | $0.22 |  CloudGPUcaptured | $0.41 9 providers | $0.009 | Deploy ↗ |
| NVIDIA T4 · 16 GB | $0.24 |  immers.cloudcaptured | $0.55 19 providers | $0.015 | Deploy ↗ |
| NVIDIA RTX 2000 Ada · 16 GB | $0.24 from |  GPU.aicaptured | $0.24 2 providers | $0.015 | Deploy ↗ |
| NVIDIA V100 · 16 GB | $0.24 |  Verdacaptured | $0.83 13 providers | $0.015 | Deploy ↗ |
| NVIDIA RTX A5000 · 24 GB | $0.27 from | GPU.ai captured | $0.58 10 providers | $0.011 | Deploy ↗ |
| NVIDIA L4 · 24 GB | $0.28 GPU only |  Hikubecaptured | $0.80 23 providers | $0.012 | Deploy ↗ |
40 more cards qualify, dearer: NVIDIA RTX 4000 Ada $0.28, NVIDIA GeForce RTX 4070 Ti SUPER $0.29, NVIDIA GeForce RTX 4080 $0.31, NVIDIA Quadro RTX 6000 $0.31, NVIDIA A10 $0.34, NVIDIA RTX 4090 $0.35, NVIDIA RTX A6000 $0.35, NVIDIA GeForce RTX 5080 $0.37, NVIDIA A40 $0.39, NVIDIA RTX 4000 SFF Ada $0.44, NVIDIA GeForce RTX 3090 Ti $0.46, NVIDIA RTX 5090 $0.50, NVIDIA L40S $0.63, NVIDIA RTX 6000 Ada $0.65, NVIDIA RTX PRO 6000 Blackwell $0.65, NVIDIA A100 40GB $0.69, NVIDIA RTX PRO 4500 Blackwell $0.72, NVIDIA L40 $0.78, NVIDIA GB10 (DGX Spark) $0.79, NVIDIA RTX PRO 5000 Blackwell $0.80, NVIDIA RTX 5000 Ada Generation $0.83, NVIDIA A100 80GB $0.92, NVIDIA A10G $1.01, Intel Gaudi 2 $1.10, AMD Instinct MI300X $1.71, NVIDIA H100 80GB (form factor not stated) $1.72, NVIDIA H100 SXM $1.79, NVIDIA RTX PRO 6000 Blackwell Max-Q $1.80, NVIDIA H100 PCIe $1.98, AMD Instinct MI325X $2.25, NVIDIA GH200 $2.29, NVIDIA H200 $2.29, NVIDIA H100 NVL $2.92, AMD Instinct MI355X $2.95, NVIDIA H200 NVL $3.29, AMD Instinct MI350X $4.00, NVIDIA B200 $4.50, NVIDIA B300 $5.89, NVIDIA GB200 NVL72 $6.94, NVIDIA GB300 NVL72 $13.30.
FLUX.1 [dev] at 16-bit
12 billion parameters × 2 bytes = 24 GB for the transformer alone, with its text encoders on top: a card with more than 24 GB holds it without offloading.
| Card, memory | Cheapest on-demand | Provider, read | Median rate card | $ per GB-hour | Deploy |
|---|---|---|---|---|---|
| NVIDIA V100 32GB · 32 GB | $0.16 | Geodd captured | $1.15 11 providers | $0.005 | Deploy ↗ |
| NVIDIA RTX A6000 · 48 GB | $0.35 |  Thunder Computecaptured | $0.59 21 providers | $0.007 | Deploy ↗ |
| NVIDIA A40 · 48 GB | $0.39 | CloudGPU captured | $0.64 8 providers | $0.008 | Deploy ↗ |
| NVIDIA RTX 5090 · 32 GB | $0.50 | OpenRelay captured | $0.79 23 providers | $0.016 | Deploy ↗ |
| NVIDIA L40S · 48 GB | $0.63 |  CloudRiftcaptured | $1.42 40 providers | $0.013 | Deploy ↗ |
| NVIDIA RTX 6000 Ada · 48 GB | $0.65 from | GPU.ai captured | $1.03 12 providers | $0.014 | Deploy ↗ |
| NVIDIA RTX PRO 6000 Blackwell · 96 GB | $0.65 from |  Hostingercaptured | $2.20 42 providers | $0.007 | Deploy ↗ |
| NVIDIA A100 40GB · 40 GB | $0.69 from |  Trooper.AIcaptured | $1.99 22 providers | $0.017 | Deploy ↗ |
| NVIDIA RTX PRO 4500 Blackwell · 32 GB | $0.72 from | GPU.ai captured | $0.86 6 providers | $0.022 | Deploy ↗ |
| NVIDIA L40 · 48 GB | $0.78 from | GPU.ai captured | $0.97 11 providers | $0.016 | Deploy ↗ |
21 more cards qualify, dearer: NVIDIA GB10 (DGX Spark) $0.79, NVIDIA RTX PRO 5000 Blackwell $0.80, NVIDIA RTX 5000 Ada Generation $0.83, NVIDIA A100 80GB $0.92, Intel Gaudi 2 $1.10, AMD Instinct MI300X $1.71, NVIDIA H100 80GB (form factor not stated) $1.72, NVIDIA H100 SXM $1.79, NVIDIA RTX PRO 6000 Blackwell Max-Q $1.80, NVIDIA H100 PCIe $1.98, AMD Instinct MI325X $2.25, NVIDIA GH200 $2.29, NVIDIA H200 $2.29, NVIDIA H100 NVL $2.92, AMD Instinct MI355X $2.95, NVIDIA H200 NVL $3.29, AMD Instinct MI350X $4.00, NVIDIA B200 $4.50, NVIDIA B300 $5.89, NVIDIA GB200 NVL72 $6.94, NVIDIA GB300 NVL72 $13.30.
How these figures are read
A card qualifies by its memory alone; speed, interconnect and software support are not ranked here. The rate is the card’s cheapest live on-demand rate card - each provider once, at its cheapest on-demand rate, community capacity and marketplace floors out, read within 48 hours - and the median is taken over the same rate cards, as on every card page. Memory figures are floors from the arithmetic above, not measurements: context length, batch size and the serving stack change them. Methodology.
Sources
- Podell et al., SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis (2023) - a 2.6B-parameter UNet
- Black Forest Labs, FLUX.1 [dev] model card - a 12 billion parameter rectified flow transformer
Other workloads: GPUs for LLM inference · GPUs for fine-tuning · GPUs for training · Cheapest GPU memory per hour.
Data updated: