Ampere consumer GPU for local AI experimentation.
Weekly median price per GPU per hour · Get the data
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.
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 3080 has 10 GB of VRAM. Even at 4-bit, the weights of most modern AI models exceed the card's usable VRAM, and context adds KV cache on top. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.
| Model | Memory (INT4 / FP4) | RTX 3080s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
3
|
–
|
–
|
Gemma 4 31B
30.7B
|
24 GB
|
3
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
8
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
20
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
27
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
34
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
172
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP16/BF16 KV cache at 32K context per request. GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.
Nvidia RTX 3080 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 59.5 TFLOPS 119 with sparsity |
| INT8 | 238 TOPS 476 with sparsity |
| FP32 | 29.8 TFLOPS |
| Precision support | FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 10 GB GDDR6X |
| Bandwidth | 760 GB/s |
| Bus width | 320-bit |
| ECC | No |
| Silicon | |
|---|---|
| Architecture | Ampere |
| Process | Samsung 8N |
| Transistors | 28.3 billion |
| Shader cores | 8,704 CUDA cores |
| Matrix cores | 272 Tensor cores |
| Compute units | 68 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 4.0 |
| Power | |
|---|---|
| Board power | 320 W |
| Cooling | Active |
Source: official Nvidia RTX 3080 datasheet.
As of October 3, 2026, the median on-demand price is $0.17 per GPU per hour across 5 providers.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 25 | $0.17 | $0.12 (in stock, Vast.ai) |
Reserved | 4 | $0.10 (1 mo, in stock, Vast.ai) |
|
Spot | 16 | $0.06 |
No median for reserved and spot: we only show this when at least 3 providers list the GPU on that billing type.
At 720 hours per month, one RTX 3080 costs an estimated $122 at the median on-demand price. Cheapest verified in stock: $86 per month on-demand, $72 reserved (1 mo), $58 spot.
GetDeploying currently tracks RTX 3080 configs from 5 providers. The cheapest verified in-stock on-demand configs come from Vast.ai, GPU.ai, Runpod and Theta EdgeCloud. See the full price comparison above for every provider and config.
More than one: even at 4-bit, the weights of most modern AI models exceed one RTX 3080's usable VRAM, and context adds KV cache on top. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
10GB or 12GB GDDR6X with Ampere Tensor Cores. Budget option for local AI experimentation.
10-12GB VRAM limits model sizes. No FP8. Subject to Nvidia's consumer EULA, which may restrict data center use.
Nvidia RTX 4070
12 GB GDDR6X · 34% less bandwidth than the RTX 3080
Nvidia RTX 3080 Ti
12 GB GDDR6X · 20% more bandwidth than the RTX 3080
Nvidia RTX 3070 Ti
8 GB GDDR6X · 20% less bandwidth than the RTX 3080
Last updated
