Inference

VRAM & speed

Whether a model fits, and how fast it will decode once it does. Uses the real attention shape of each model — grouped-query head counts, sliding windows, MoE routing, MLA latents — because those change the answer by multiples, not percentages.

Configuration

Hardware

Multi-GPU split

Total memory

Decode

tok/s

Prefill

tok/s

Max context

that fits entirely in memory

Memory breakdown

0
    Table view & working
    Memory breakdown
    Component Size Share How it is derived

    Quantisation ladder

    Same model and context, every quantisation level
    Quant Weights Total Fits Decode Max ctx

    Rows are the same model at the same context on the same hardware — only the weight precision changes. The highlighted row is your current selection.

    Context scaling

    Same model and quantisation, varying context
    Context KV cache Total Fits Decode Time to first token

    What this assumes

    • Decode is memory-bound. Speed is bytes read per token divided by achieved bandwidth, where bytes read is the active weights plus the whole KV cache. That last term is why a model runs slower at 100k context than at zero, which most calculators never show you.
    • Prefill is compute-bound. Two FLOPs per active parameter per token, against dense FP16 tensor throughput at a realistic 45% MFU. Marketing FLOPS numbers assume 2:1 sparsity that no LLM runtime achieves; the figures here do not.
    • Bits-per-weight are measured, not nominal. Q4_K_M is 4.83 bpw in real files, not 4.00 — K-quants carry block scales and keep some tensors at higher precision. Using the nominal width underestimates every K-quant by 15–20%.
    • Sliding-window and MLA models are modelled properly. Gemma 3 keeps a 1024-token window on five of every six layers, and DeepSeek compresses KV to a 576-value latent. Treating either as plain GQA overstates the cache by up to 10×.
    • Expect ±20%. These are calibrated first-principles estimates, not benchmarks. Runtime, driver, kernel and flash-attention choices all move the number. Use it to decide what to download; use a real benchmark to decide what to ship.