GeForce RTX 3080
The GeForce RTX 3080 is a cloud GPU with 10 GB of memory and 320 W TDP. It is currently available from 1 provider starting at $0.11/hr, with a market median of $0.11/hr across 1 offering.
Best deal
Hardware specifications
- Architecture
- Ampere
- VRAM
- 10 GB
- Memory type
- GDDR6X
- Memory bandwidth
- 760 GB/s
- FP32
- 30 TFLOPS
- TDP
- 320 W
Same across all providers.
Market comparison
Offerings
| Provider | Cloud | Count | vCPU | RAM | Region | Per GPU hr | SPOT | Total/hr | |
|---|---|---|---|---|---|---|---|---|---|
AI Galaxy 0.0% 30dReferral link | — | ×1 | — | — | CN | $0.11/hr | — | $0.11/hr | Launch ↗ |
LLMs that fit
| Model | Params | 16-bit | 8-bit | 4-bit |
|---|---|---|---|---|
Llama 3.1 70B Meta | 70B | Needs >8 GPUs | Needs >8 GPUs | Barely fits on 6× |
Qwen3.6 35B-A3B Alibaba | 35B 3B active | Needs >8 GPUs | Barely fits on 6× | 4× · 6.4 GB free |
Qwen3 32B Alibaba | 32.8B | Needs >8 GPUs | 6× · 14% spare | Barely fits on 3× |
Qwen2.5 14B Alibaba | 14B | Barely fits on 4× | Barely fits on 2× | 2× · 8.6 GB free |
Llama 3.1 8B Meta | 8B | 3× · 9.1 GB free | 2× · 8.6 GB free | 1× · 3.3 GB free |
Mistral 7B Mistral AI | 7B | Barely fits on 2× | Barely fits on 1× | 1× · 4.1 GB free |
Qwen3 4B Alibaba | 4B | 2× · 8.4 GB free | 1× · 3.6 GB free | 1× · 6.3 GB free |
Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput.
Similar GPUs
See more GPUs like this in
Frequently asked questions
How much does the GeForce RTX 3080 cost per hour?
The cheapest GeForce RTX 3080 offering starts at $0.11/hr, and the market median is $0.11/hr.
Which cloud providers offer the GeForce RTX 3080?
We track GeForce RTX 3080 offerings from AI Galaxy.
How much VRAM does the GeForce RTX 3080 have?
The GeForce RTX 3080 has 10 GB of VRAM.
What LLMs can run on the GeForce RTX 3080?
With 10 GB of VRAM, the GeForce RTX 3080 can run 7 of our tracked models in 4-bit quantization, including Qwen3.6 35B-A3B, Qwen3 32B, Llama 3.1 70B. 4 models fit in 16-bit precision.
What's the biggest LLM I can run on multiple GeForce RTX 3080s?
With 8× GeForce RTX 3080 (80 GB total), the largest tracked model that fits in 16-bit is Llama 3.1 8B (8B params), which needs 3× GPUs.
Where is the GeForce RTX 3080 cheapest?
The cheapest GeForce RTX 3080 offering in our catalog is AI Galaxy at $0.11/hr per GPU-hour (×1).