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

Quadro P4000

NVIDIA

8GB VRAM · 243 GB/s bandwidth · 0.1 FP16 TFLOPS · 105W TDP

The Quadro P4000 has 8GB of VRAM with 243 GB/s memory bandwidth and 0.1 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (60 tok/s), Qwen 2.5 7B (32 tok/s), Llama 3.1 8B (30 tok/s). Models larger than ~14B parameters won't fit even at Q4. Electricity cost is approximately $11/month at 105W TDP.

What LLMs can you run?

ModelParamsQ4 WeightFitDecode
Gemma 3 4B4.0B2 GBcomfortable60 tok/s
Qwen 2.5 7B7.6B4 GBcomfortable32 tok/s
Llama 3.1 8B8.0B4 GBcomfortable30 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 3060 8 GB8GB240 GB/s12.7170W
GeForce RTX 3060 8 GB GA1048GB240 GB/s12.7195W
Radeon PRO W75008GB256 GB/s24.470W
Radeon RX 6600 XT8GB256 GB/s21.2160W
GeForce GTX 10708GB256 GB/s0.1150W

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