AI Models You Can Run on NVIDIA B200 GPU

Llama 3.1 70B Instruct is the highest-rated model that runs on NVIDIA B200 GPU at 4-bit, at about 57 tok/s. In total, NVIDIA B200 GPU can run 159 of the 169 open models we track.

We size each model at 4-bit (Q4_K_M), add the KV cache for its context length and a fixed runtime overhead, then compare that to this device VRAM. Each model is graded on how comfortably it fits and how fast it should run on this card.

It is an estimate of decode speed in tokens per second at 4-bit, based on this device memory bandwidth and each model size. Real speed depends on your runtime, batch size, and context length, so use it to compare models, not as a hard promise.

Lower-bit quantization shrinks a model so more of them fit. These grades already assume 4-bit, which is the common local default. Going below 4-bit can squeeze a larger model in at some quality cost; going above needs more VRAM and may not fit.