vram.run Models Hardware Providers Cloud State of Inference
API provider data is live · Hardware & cloud pricing curated 2026-02-23

GeForce GTX 1080

NVIDIA

8GB VRAM · 320 GB/s bandwidth · 0.1 FP16 TFLOPS · 180W TDP

The GeForce GTX 1080 has 8GB of VRAM with 320 GB/s memory bandwidth and 0.1 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (80 tok/s), Qwen 2.5 7B (42 tok/s), Llama 3.1 8B (39 tok/s). Models larger than ~14B parameters won't fit even at Q4. Electricity cost is approximately $19/month at 180W TDP.

What LLMs can you run?

ModelParamsQ4 WeightFitDecode
Gemma 3 4B4.0B2 GBcomfortable80 tok/s
Qwen 2.5 7B7.6B4 GBcomfortable42 tok/s
Llama 3.1 8B8.0B4 GBcomfortable39 tok/s
Mistral Small 24B24.0B12 GBwon't fit
Gemma 3 27B27.4B14 GBwon't fit
Qwen 2.5 Coder 32B32.5B16 GBwon't fit
Llama 3.3 70B70.6B35 GBwon't fit
Qwen 2.5 72B72.7B36 GBwon't fit
Llama 3.1 405B405B202 GBwon't fit
DeepSeek R1 671B671B336 GBwon't fit

Similar GPUs

GPUVRAMBWTFLOPSTDP
GeForce RTX 50508GB320 GB/s13.2130W
Radeon RX 90608GB322 GB/s42.9132W
Radeon RX 9060 XT 8 GB8GB322 GB/s51.3150W
GeForce GTX 1080 11Gbps8GB352 GB/s0.1180W
Radeon PRO W76008GB288 GB/s40.0130W

Compare with another GPU

Select another GPU to compare specs and model performance side by side.

Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0