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 AMD RX 9070 XT 16GB: Top match: Qwen3 8B at Q6_K, Good fit. About 54.2 t/s (estimated). As of 22 Nov 2026.
16 GB VRAM·32 GB system RAM·640 GB/s·195 TFLOPS fp16
Get a weekly email of new AMD RX 9070 XT 16GB reports and newly released models that fit it.
Email me new reportsWhat people with 16 GB of VRAM actually run: best local LLMs for 16 GB of VRAM →
People have run Qwen3 8B on the AMD RX 9070 XT 16GB and reported their speeds.
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.