37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
C avx2ccpu-inferenceggufinference-enginelinuxllmlocal-llmmixture-of-expertsmoenvmequantizationqwen3simdspeculative-decodingvulkan
{
"compilerOptions": {
"strict": true,
"target": "es2022",
"noUncheckedIndexedAccess": true,
"noImplicitOverride": true,
"noFallthroughCasesInSwitch": true,
"verbatimModuleSyntax": true,
"isolatedModules": true,
"forceConsistentCasingInFileNames": true,
"skipLibCheck": true,
"rootDir": "src"
}
}