cpu-inference

Phocinae-Largha-150M-v1

+124

斑海豹 — Phocinae-Largha-150M-v1: a 144.3M bilingual decision model. Tiny model. Big decisions. 小海豹，大决断。

janas

+40

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.

kimi-k3-in-c

+82

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

feder-cr/jev

+37

jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.

MOSS-TTS-Nano

+39

A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation

franken_ocr

+8

Pure-Rust, CPU-only OCR engine for Baidu Unlimited-OCR (a DeepSeek-OCR-derived 3B MoE VLM). Five-model zoo, custom int8 kernels, no ML framework, no Python, no GPU.