What GPU do I need to run it?

How the VRAM and cost numbers are calculated

• Weight bytes = parameter count × bytes-per-parameter for the shown precision (FP32=4, BF16/FP16=2, FP8=1, INT4=0.5 bytes).
• Required VRAM adds a flat 1.2× overhead on top of weight size for KV-cache, activations, and allocator fragmentation, calibrated for an assumed 8,192-token context — a rule-of-thumb, not a per-request simulation. Long contexts or large batch sizes need materially more headroom.
• “Cheapest live fit” only matches a GPU to a row if its hardware actually supports that row's compute format — a pre-Ampere card (Pascal/Volta/Turing) never qualifies for a BF16 or FP8 row, regardless of VRAM or price — and caps a fit at 8 GPUs of the same model. See the GPU Index for per-model specs.
• The INT4 row additionally requires a GPU with AWQ/GPTQ/ Marlin-class quantized-serving kernel support AND a quantized checkpoint that's actually been published for the model in question — neither is guaranteed, so check the model's Hugging Face page for a published INT4/AWQ/GPTQ variant before relying on that row.
• Prices are live per-GPU $/hr rates from Aquanode's marketplace feed, normalized the same way as the GPU Index, with outlier offers excluded.
• Multi-GPU fits assume the model shards cleanly across cards (e.g. tensor parallelism) — real throughput and interconnect overhead aren't modeled.