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

H200 NVL

NVIDIA

141GB VRAM · 4890 GB/s bandwidth · 241.3 FP16 TFLOPS · 600W TDP

The H200 NVL has 141GB of VRAM with 4890 GB/s memory bandwidth and 241.3 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (1760 tok/s), Qwen 2.5 7B (926 tok/s), Llama 3.1 8B (876 tok/s). Models larger than ~240B parameters won't fit even at Q4. Electricity cost is approximately $65/month at 600W TDP.

What LLMs can you run?

ModelParamsQ4 WeightFitDecode
Gemma 3 4B4.0B2 GBcomfortable1760 tok/s
Qwen 2.5 7B7.6B4 GBcomfortable926 tok/s
Llama 3.1 8B8.0B4 GBcomfortable876 tok/s
Mistral Small 24B24.0B12 GBcomfortable293 tok/s
Gemma 3 27B27.4B14 GBcomfortable256 tok/s
Qwen 2.5 Coder 32B32.5B16 GBcomfortable216 tok/s
Llama 3.3 70B70.6B35 GBcomfortable99 tok/s
Qwen 2.5 72B72.7B36 GBcomfortable96 tok/s
Llama 3.1 405B405B202 GBwon't fit
DeepSeek R1 671B671B336 GBwon't fit

Similar GPUs

GPUVRAMBWTFLOPSTDP
H200 SXM 141 GB141GB4890 GB/s267.6700W
B300144GB4099 GB/s1231.81400W
Radeon Instinct MI250128GB3280 GB/s362.1500W
Radeon Instinct MI250X128GB3280 GB/s383.0500W
Radeon Instinct MI300128GB6550 GB/s383.0600W

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