Cheapest GPU memory per hour
As of — Every card, cheapest GB first: from $0.005 per GB of memory per hour on the NVIDIA V100 32GB (32 GB at $0.16 on Geodd), 72 cards. 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.
When the job is limited by memory - a model that has to fit, a batch that has to be large - the figure to compare is the price per GB of GPU memory per hour: the cheapest on-demand rate for a card divided by its memory. Speed is not in it: a cheaper GB on an older card can take longer to use.
Every card, cheapest GB first
Each card’s cheapest live on-demand rate divided by its memory.
| Card, memory | Cheapest on-demand | Provider, read | Median rate card | $ per GB-hour | Deploy |
|---|---|---|---|---|---|
| NVIDIA V100 32GB · 32 GB | $0.16 |  Geoddcaptured | $0.76 8 providers | $0.005 | Deploy ↗ |
| NVIDIA GeForce RTX 3060 · 12 GB | $0.07 |  Edgevanacaptured | — 1 provider | $0.006 | Deploy ↗ |
| NVIDIA GeForce GTX 1080 Ti · 11 GB | $0.07 | Edgevana captured | $0.15 2 providers | $0.006 | Deploy ↗ |
| NVIDIA TITAN Xp · 12 GB | $0.08 | Edgevana captured | — 1 provider | $0.006 | Deploy ↗ |
| NVIDIA RTX PRO 6000 Blackwell · 96 GB | $0.65 from |  Hostingercaptured | $2.20 35 providers | $0.007 | Deploy ↗ |
| NVIDIA GeForce RTX 3090 · 24 GB | $0.17 | Edgevana captured | $0.50 8 providers | $0.007 | Deploy ↗ |
| NVIDIA GeForce GTX 1080 · 8 GB | $0.06 | Edgevana captured | — 1 provider | $0.007 | Deploy ↗ |
| NVIDIA RTX A6000 · 48 GB | $0.35 |  Thunder Computecaptured | $0.55 17 providers | $0.007 | Deploy ↗ |
| NVIDIA RTX A4000 · 16 GB | $0.12 from |  GPU.aicaptured | $0.17 9 providers | $0.007 | Deploy ↗ |
| NVIDIA GeForce GTX 1070 Ti · 8 GB | $0.07 | Edgevana captured | — 1 provider | $0.009 | Deploy ↗ |
| NVIDIA GeForce RTX 5060 Ti · 16 GB | $0.14 | Edgevana captured | — 1 provider | $0.009 | Deploy ↗ |
| AMD Instinct MI325X · 256 GB | $2.25 |  Bentauscaptured | $2.25 3 providers | $0.009 | Deploy ↗ |
| AMD Instinct MI300X · 192 GB | $1.71 from |  TensorWavecaptured | $2.81 8 providers | $0.009 | Deploy ↗ |
| NVIDIA Tesla P100 12GB · 12 GB | $0.11 | Edgevana captured | — 1 provider | $0.009 | Deploy ↗ |
| NVIDIA GeForce RTX 2060 12GB · 12 GB | $0.11 | Edgevana captured | — 1 provider | $0.009 | Deploy ↗ |
| NVIDIA GeForce RTX 4060 Ti · 16 GB | $0.15 | Edgevana captured | — 1 provider | $0.010 | Deploy ↗ |
| NVIDIA T4 · 16 GB | $0.15 | Edgevana captured | $0.53 13 providers | $0.010 | Deploy ↗ |
| NVIDIA RTX 4000 Ada · 20 GB | $0.20 | Edgevana captured | $0.28 5 providers | $0.010 | Deploy ↗ |
| NVIDIA TITAN RTX · 24 GB | $0.24 | Edgevana captured | — 1 provider | $0.010 | Deploy ↗ |
| AMD Instinct MI355X · 288 GB | $2.95 from | TensorWave captured | $5.99 3 providers | $0.010 | Deploy ↗ |
52 more cards qualify, dearer: NVIDIA L40 $0.53, NVIDIA A100 80GB $0.89, NVIDIA Quadro RTX 6000 $0.27, NVIDIA GeForce RTX 4060 $0.09, NVIDIA RTX A5000 $0.27, NVIDIA L4 $0.27, NVIDIA GeForce RTX 4070 SUPER $0.14, NVIDIA RTX PRO 4500 Blackwell $0.39, NVIDIA A2 $0.20, NVIDIA A40 $0.59, NVIDIA GeForce RTX 4070 $0.15, NVIDIA V100 $0.21, NVIDIA GeForce RTX 3080 $0.13, NVIDIA A30 $0.32, NVIDIA A10 $0.32, NVIDIA RTX 6000 Ada $0.65, NVIDIA GeForce RTX 5060 $0.11, AMD Instinct MI350X $4.00, NVIDIA RTX 5000 Ada Generation $0.45, NVIDIA GeForce RTX 5070 Ti $0.23, NVIDIA RTX PRO 5000 Blackwell $0.71, NVIDIA H200 $2.09, NVIDIA RTX 2000 Ada $0.24, NVIDIA GeForce RTX 3060 Ti $0.12, NVIDIA L40S $0.72, NVIDIA GeForce RTX 4080 $0.24, NVIDIA RTX 4090 $0.39, NVIDIA RTX 5090 $0.54, NVIDIA B300 $4.89, NVIDIA GeForce RTX 3070 $0.14, NVIDIA RTX PRO 6000 Blackwell Max-Q $1.80, NVIDIA GeForce RTX 5080 $0.30, NVIDIA A100 40GB $0.76, NVIDIA GeForce RTX 3090 Ti $0.46, NVIDIA GeForce RTX 5070 $0.23, NVIDIA B200 $3.69, NVIDIA GeForce RTX 3080 Ti $0.24, NVIDIA GeForce RTX 2080 Ti $0.23, NVIDIA H100 80GB (form factor not stated) $1.71, NVIDIA RTX 4000 SFF Ada $0.44, NVIDIA H100 SXM $1.79, NVIDIA RTX 4500 Ada Generation $0.54, NVIDIA H100 PCIe $1.83, NVIDIA GeForce RTX 4080 SUPER $0.37, NVIDIA H200 NVL $3.29, NVIDIA GH200 $2.29, NVIDIA RTX A2000 $0.15, NVIDIA H100 NVL $2.92, NVIDIA GB300 NVL72 $10.74, NVIDIA GB200 NVL72 $6.94, NVIDIA GeForce RTX 4070 Ti SUPER $0.62, NVIDIA A10G $1.00.
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.
Other workloads: GPUs for LLM inference · GPUs for fine-tuning · GPUs for training · GPUs for image generation.
Data updated: