High-end Ada Lovelace consumer GPU for local AI and gaming.
Weekly median price per GPU per hour
By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.
What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.
Within a group, five factors set the order:
We match the provider, its country, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.
Singapore
4 configs
1x-8x
USA
9 configs
1x
Switzerland
1 config
1x
USA
1 config
1x
No providers match .
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price.
One RTX 4080 has 16 GB of VRAM. In practice, that's enough memory for roughly 15B parameters at 4-bit or 2B at 16-bit, assuming a 32K context. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.
| Model | Memory (INT4 / FP4) | RTX 4080s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
18 GB
|
2
|
–
|
–
|
Gemma 4 31B
30.7B
|
22 GB
|
2
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
67 GB
|
5
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
13
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
239 GB
|
17
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
22
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,544 GB
|
108
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP8 KV cache at 32K context per request (FP16/BF16 in the 16-bit column). GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.
Nvidia RTX 4080 · Per GPU
| Compute · dense | |
|---|---|
| FP8 | 194.9 TFLOPS 389.8 with sparsity |
| FP16 / BF16 | 97.5 TFLOPS 195 with sparsity |
| INT8 | 389.9 TOPS 779.8 with sparsity |
| FP32 | 48.7 TFLOPS |
| Precision support | FP8FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 16 GB GDDR6X |
| Bandwidth | 717 GB/s |
| Bus width | 256-bit |
| ECC | No |
| Silicon | |
|---|---|
| Architecture | Ada Lovelace |
| Process | TSMC 4N |
| Transistors | 45.9 billion |
| Shader cores | 9,728 CUDA cores |
| Matrix cores | 304 Tensor cores |
| Compute units | 76 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 4.0 |
| Power | |
|---|---|
| Board power | 320 W |
| Cooling | Active |
Source: official Nvidia RTX 4080 datasheet.
As of September 13, 2026, the median on-demand price is $0.25 per GPU per hour across 5 providers with a priced on-demand config.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 14 | $0.25 | $0.22 (in stock, Vast.ai) |
Spot | 5 | $0.11 (in stock, Salad) |
No median for spot: we only show this when at least 3 providers list the GPU on that billing type.
At 720 hours per month, one RTX 4080 costs an estimated $180 at the median on-demand price. Cheapest verified in stock: $158 per month on-demand, $79 spot.
GetDeploying currently tracks RTX 4080 configs from 6 providers. The cheapest verified in-stock on-demand configs come from Vast.ai, Salad, GPUhub and Theta EdgeCloud. See the full price comparison above for every provider and config.
As of September 13, 2026, the median on-demand price has been flat over the past 90 days, at about $0.25 per GPU per hour.
One RTX 4080 runs models up to roughly 15B parameters at 4-bit quantization or 2B at 16-bit, assuming a 32K context. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
16GB GDDR6X with Ada Lovelace FP8 support. Good consumer option for local AI development and image generation.
16GB VRAM limits model sizes. No ECC. Subject to Nvidia's consumer EULA, which may restrict data center use. For AI workloads beyond local development, consider data center GPUs.
Last updated