RTX 3090 rental prices: cheapest $/hr today
The cheapest on-demand RTX 3090 rental today is $0.20/hr on TensorDock for the RTX 3090, updated 2026-10-06. 24 GB VRAM, NVIDIA.
Salad prices use its Lowest priority tier: workloads can be interrupted. These rates suit retryable batch jobs; they do not guarantee availability or uninterrupted runtime. Compare Salad priority tiers.
Pricing at a glance
All current RTX 3090 offers
Provider, memory & availability
| GPU / provider | Billing | $/GPU-hour | GPUs / total per hour | Availability / details |
|---|---|---|---|---|
| RTX 3090SaladCloud24 GB VRAM | community cloud | $0.09per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| RTX 3090 TiSaladCloud24 GB VRAM | community cloud | $0.10per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| RTX 3090TensorDock24 GB VRAM | on-demand | $0.20per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| RTX 3090RunPod24 GB VRAM | community cloud | $0.22per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| RTX 3090 TiRunPod24 GB VRAM | community cloud | $0.27per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| RTX 3090RunPod24 GB VRAM | secure cloud | $0.50per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
Try another provider or reduce the minimum memory.
Tables rank by price, lowest first. Commercial relationships never affect ordering. How we collect and rank prices.
Monthly view assumes 730 hours of continuous use. Daily view assumes 24 hours.
On-demand and secure rates do not require a reservation. Community and spot capacity can be interrupted. Prices are per GPU per hour, before storage/egress. Every row shows its update date.
RTX 3090 hardware specs
| Architecture | Ampere |
|---|---|
| VRAM | 24 GB |
| FP16 TFLOPS (dense) | 142 |
| Memory bandwidth | 936 GB/s |
| TDP | 350 W |
| Interconnect | PCIe Gen4 |
| Launched | 2020 |
Datasheet spec for the RTX 3090 variant. Source: www.nvidia.com.
Compare RTX 3090 configurations
RTX 3090 purchase prices · Rent or buy calculator · Compare two GPUs
LLM memory estimates for this GPU
These models have an estimated inference footprint within 24 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.
| Model | 16-bit GB | 8-bit GB | 4-bit GB |
|---|---|---|---|
| Qwen2.5 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
| Qwen2.5 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen2.5 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen2.5 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| Qwen2.5 14B | 36.4 | 18.7 ✓ | 9.8 ✓ |
| Qwen2.5 32B | 79.9 | 40.6 | 20.9 ✓ |
| Qwen2.5 Coder 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
| Qwen2.5 Coder 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen2.5 Coder 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen2.5 Coder 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| Qwen2.5 Coder 14B | 36.4 | 18.7 ✓ | 9.8 ✓ |
| Qwen2.5 Coder 32B | 79.9 | 40.6 | 20.9 ✓ |
| Qwen3 0.6B | 2.4 ✓ | 1.5 ✓ | 1.0 ✓ |
| Qwen3 1.7B | 5.4 ✓ | 3.0 ✓ | 1.8 ✓ |
| Qwen3 4B | 10.4 ✓ | 5.6 ✓ | 3.1 ✓ |
| Qwen3 8B | 20.4 ✓ | 10.6 ✓ | 5.6 ✓ |
| Qwen3 14B | 36.2 | 18.5 ✓ | 9.7 ✓ |
| Qwen3 32B | 79.9 | 40.6 | 20.9 ✓ |
| Qwen3 30B A3B | 73.8 | 37.1 | 18.8 ✓ |
| DeepSeek R1 Distill Qwen 1.5B | 4.4 ✓ | 2.3 ✓ | 1.2 ✓ |
| DeepSeek R1 Distill Qwen 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| DeepSeek R1 Distill Qwen 14B | 36.4 | 18.7 ✓ | 9.8 ✓ |
| DeepSeek R1 Distill Qwen 32B | 79.9 | 40.6 | 20.9 ✓ |
| DeepSeek R1 Distill Llama 8B | 19.9 ✓ | 10.3 ✓ | 5.5 ✓ |
| Mistral 7B v0.3 | 18.0 ✓ | 9.3 ✓ | 5.0 ✓ |
| Mistral Small 24B 2501 | 57.4 | 29.1 | 14.9 ✓ |
| Mistral Nemo 2407 | 30.2 | 15.5 ✓ | 8.2 ✓ |
| phi 4 | 36.2 | 18.6 ✓ | 9.8 ✓ |
Compare model memory requirements or change context and memory assumptions on a model's page.
When to choose RTX 3090
Use the model memory estimates above to check whether your weights, context and batch size fit within 24 GB. Then compare the exact variant, node size and software support. Capacity alone does not establish inference speed or training throughput.
If your workload fits within 16 GB, compare RTX A4000 rental prices from $0.10/GPU-hour. The smaller memory budget is the trade-off; price alone does not make the cards interchangeable.
RTX 3090 price changes
- 30 days: 0.0% across 2 matching firm-price configurations since 2026-09-06.
- 90 days: 8.7% across 1 matching firm-price configurations since 2026-07-08.
Changes use the geometric mean of price ratios for the same provider, variant, tier, GPU count, instance and region. New listings are not counted as price changes.
Price history
on-demand rate per day · median on-demand rate per day (dashed), since 2026-07-05: $0.16 low · $0.46 high. Full ledger on the history hub.
FAQ
The cheapest RTX 3090 rental we have is $0.20 per GPU-hour on TensorDock (on-demand), updated 2026-10-06.
24 GB depending on the variant (RTX 3090: 24 GB, RTX 3090 Ti: 24 GB).
TensorDock has the cheapest verified on-demand rate today at $0.20 per GPU-hour; interruptible spot/community capacity starts at $0.09. Verified 2026-10-06.
Related
All 24 GB+ GPUs · GPUs under $1/hr · Price movers this week · TensorDock review · RTX 3090 vs RTX 4090 · RTX 3090 vs RTX 5090 · RTX 3090 vs RTX 5080
Should you rent or buy?
Compare RTX 3090 purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates.