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

GeForce RTX 4060 AD106

NVIDIA

8GB VRAM · 272 GB/s bandwidth · 15.1 FP16 TFLOPS · 115W TDP

The GeForce RTX 4060 AD106 has 8GB of VRAM with 272 GB/s memory bandwidth and 15.1 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (88 tok/s), Qwen 2.5 7B (46 tok/s), Llama 3.1 8B (44 tok/s). Models larger than ~14B parameters won't fit even at Q4. Electricity cost is approximately $12/month at 115W TDP.

What LLMs can you run?

ModelParamsQ4 WeightFitDecode
Gemma 3 4B4.0B2 GBcomfortable88 tok/s
Qwen 2.5 7B7.6B4 GBcomfortable46 tok/s
Llama 3.1 8B8.0B4 GBcomfortable44 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 40608GB272 GB/s15.1115W
Radeon RX 6650 XT8GB280 GB/s21.6176W
GeForce GTX 10708GB256 GB/s0.1150W
GeForce GTX 1070 GDDR5X8GB256 GB/s0.1150W
GeForce GTX 1070 Ti8GB256 GB/s0.1180W

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