llamaperf

LLM VRAM calculator

Pick your GPU or Mac and what you use models for. Every open-weight model the site knows is sized for your hardware, graded on fit, given a speed estimate from its memory bandwidth, and ranked by how well it matches the job. A Mac is graded against the memory macOS lets its GPU use, not all of it. Where community benchmarks exist on the same card, the measured number replaces the estimate.

On the NVIDIA RTX PRO 6000 Max-Q (96GB): Nothing fits at these settings. As of 22 Nov 2026.

Hardware

96 GB VRAM·32 GB system RAM·1,792 GB/s·439 TFLOPS fp16

Balanced: quality first, then speed.

Get a weekly email of new NVIDIA RTX PRO 6000 Max-Q reports and newly released models that fit it.

Email me new reports

What people with 96 GB of VRAM actually run: best local LLMs for 96 GB of VRAM →

0 perfect·0 good·0 marginal·3 too tight
Sort

Nobody has reported DeepSeek V4.1 Flash 1017B on the NVIDIA RTX PRO 6000 Max-Q yet.

Memory assumes an F16 KV cache at 32k context; Perfect is under 60% of the pool, Good under 85%, Marginal under 98%. Offload paths cap at Good. Click a row for the breakdown.

Did this help you choose a setup?

Optional feedback. No account needed.