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.
192 GB unified memory·273 GB/s·61.4 TFLOPS fp16
Unified memory: the 192 GB pool is shared with the GPU, so there is no separate RAM to offload into.
Get a weekly email of new AMD Gorgon Halo 192GB reports and newly released models that fit it.
Email me new reportsNobody has reported Llama 3.2 1B on the AMD Gorgon Halo 192GB 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. Speed is the memory bandwidth divided by the bytes read per token, at 55% efficiency (llmfit's generic figure); a community median at the same quant replaces it. Click a row for the breakdown.
Did this help you choose a setup?
Optional feedback. No account needed.