What LLMs can the RTX 6000 Ada Generation run?

59 of the 62 open models in this roster have an on-device configuration with usable context. The largest by exact parameter count is Qwen2.5 72B Instruct at Q3_K_M, with room for 29k tokens. “Largest” describes parameter count, not model quality or task performance.

The device publishes 48 GB of GDDR6 ECC. This calculator budgets 92%, or 44.2 GiB, for model weights and KV cache; the remainder is an explicit allowance for the runtime, driver or operating system, workspace, and display. It is an assumption rather than a vendor specification.

No. They are bandwidth-bound roofline ceilings: 960 GB/s divided by the bytes one decoded token actually reads, which the table prints beside every ceiling. That is not the size of the file on disk — a token reads the weights it routes through, all of them for a dense model but only the selected experts for a mixture-of-experts, plus one pass over the KV cache. Laguna XS 2.1 holds 33.2 GiB resident at Q8_0 yet reads 2.9 GiB/token, which is what produces its 305 tok/s. Real throughput is lower because kernels, cache traffic, prompt processing, scheduling, and runtime overhead also consume time.