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
/* SPDX-License-Identifier: GPL-3.0-or-later
Copyright (C) 2026 Maurizio Cammalleri */
/*
* options.c - janas-chat's options: those of the command line and of its
* settings files (see options.h).
*/
#include "options.h"
#include <string.h>
const char *chat_words_last(int n, char *const *w, const char *opt)
{
const char *v = NULL;
for (int i = 0; i + 1 < n; i++)
if (strcmp(w[i], opt) == 0)
v = w[i + 1];
return v;
}
int chat_words_any(int n, char *const *w, const char *const *opts)
{
for (int i = 0; i < n; i++)
for (int k = 0; opts[k]; k++)
if (strcmp(w[i], opts[k]) == 0)
return 1;
return 0;
}