by tamnd
Benchmarks kime against Laya, laya-mlx, laya-coreml, and Jev on matched hardware
The benchmark harness for kime. Latency, throughput, energy, cost and accuracy against Laya, laya-mlx, laya-coreml and Jev on the same hardware, with the reporting rules that decide what a number is allowed to claim.
Platforms
Use cases
Related projects
laya-mlx
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using MLX
laya-coreml
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using Core ML and the Neural Engine
openJev-verdict-2.0
Heman10x-NGU
Develops and benchmarks a non-autoregressive typed-decision model against Jev and Laya
laya-playground
wdobry
A local website combines Laya model demos, games, a benchmark, and an agent skill
keel
codejunkie99
A macOS coding workspace uses local Laya or hosted Jev to select task routes
laya-vs-jev
virajbhartiya
A side-by-side T-Rex game compares local Laya and hosted Jev decision models