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
/*
* Version information
*
* Copyright The Mbed TLS Contributors
* SPDX-License-Identifier: Apache-2.0 OR GPL-2.0-or-later
*/
#include "ssl_misc.h"
#if defined(MBEDTLS_VERSION_C)
#include "mbedtls/version.h"
#include <string.h>
unsigned int mbedtls_version_get_number(void)
{
return MBEDTLS_VERSION_NUMBER;
}
const char *mbedtls_version_get_string(void)
{
return MBEDTLS_VERSION_STRING;
}
const char *mbedtls_version_get_string_full(void)
{
return MBEDTLS_VERSION_STRING_FULL;
}
#endif /* MBEDTLS_VERSION_C */