NewChunking Qwen3.5's gated DeltaNet for 1.5x faster prefill on Apple Silicon
Benchmark

Measure every model on every chip.

Throughput, latency, power, and accuracy for every model and every chip, updated with every build.

Find your chip →

The datasheet number is not your number.

Know the chip before you buy it

Set a power budget and a frame-rate floor, and see which boards actually hit it with your model.

Track a model across builds

Watch throughput and latency move as you iterate, chip by chip.

Accuracy, not just speed

Every run reports accuracy measured on the device alongside throughput and power, so a quantization regression shows up as a number.

Measure everything that matters.

Throughput

Mean FPS over a steady-state window.

Latency

p99 in milliseconds, end to end, postprocessing included.

Power

Watts sampled at the rail.

Accuracy

mAP 50:95 on the COCO validation set for detection models.

Efficiency

FPS per watt, for the fleets that run on batteries.

Build over build

Track every metric across builds and watch a model get faster over time.

Measure it. Then ship it.

Run the matrix against your constraints and see which chips clear them.