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
Builds are not enabled for this repository.
Workflows
files in.armgit/workflows/No workflow yet. Add a file such as .armgit/workflows/build.yml:
name: Build
on: [push, pull_request, manual]
jobs:
test:
image: node:22
steps:
- name: Install
run: npm ci
- name: Test
run: npm testNo builds yet.