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.
12 GB VRAM·32 GB system RAM·456 GB/s·117 TFLOPS fp16
Get a weekly email of new Intel Arc B580 12GB reports and newly released models that fit it.
Email me new reportsWhat people with 12 GB of VRAM actually run: best local LLMs for 12 GB of VRAM →
Nobody has reported DeepSeek V4 Flash 9B on the Intel Arc B580 12GB 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.