MODEL-ADAPTIVE OPTIMIZATION FOR SPARSE INFERENCE
Mixture-of-Experts models waste most of their serving cost moving expert weights around. Strata profiles how your model routes, calibrates competing policies under an explicit quality budget, and deploys the measured winner.
RUN BIG MODELS ON THE LAPTOP YOU HAVE
Strata pages a model's experts from SSD, so a laptop runs models that would never fit in its memory. Pick your machine — see what runs, and what it costs.
3 of 3 tested models run on a 16 GB Mac · reserving ~4 GB for the OS
Too big for RAM — Strata streams experts from SSD, keeping 51% hot.
Too big for RAM — Strata streams experts from SSD, keeping 9% hot.
Loads fully in memory — runs natively, Strata paging isn't needed.
More classes landing next (paged-runtime support in progress): Mixtral-8x7B · gpt-oss-20b · Qwen3-Next-80B-A3B
Real measurement: Qwen3-30B-A3B, single node, physical cache-bypassed reads, 6 prompts × 2 runs per point. The gap is the product.
Every number carries its quality cost. When nothing beats standard routing within your budget, Strata says so.
Trace which experts your model's router actually activates, token by token, on your workload.
Sweep competing routing policies in normalized units and find each one's safe operating point under your quality budget.
Race the calibrated policies on a real fixed-memory runtime with physical reads — the measured winner is the only one that counts.
One config file, one OpenAI-compatible endpoint. Your application code doesn't change.
Across eight MoE architectures we measured, the best routing policy flips with the model, the memory budget, and the quality tolerance — including the best published method, which Strata implements as a baseline and beats or adopts per deployment. A hard-coded choice is provably wrong somewhere. A measured tournament never is.