#cpu-inference Repositories
Discover 17 active open source GitHub repositories tagged with #cpu-inference, accumulating 84,398 total stars (averaging 4,964 stars per project). Leading this topic is microsoft/BitNet with 42,358 stars.
17 repositories total
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.
Offline translation model server with low resource consumption, fast speed, and private deployment capability. ไฝ่ตๆบๅ ็จ้ๅบฆๅฟซๅฏ็งๆ้จ็ฝฒ็็ฆป็บฟ็ฟป่ฏๆจกๅๆๅกๅจ
A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation
Zero-GPU CPU inference for 30Bโ284B MoE models (Qwen3.8 176.5B cold-cache certified in 28.26/48.35 GiB Cgroup v2, DeepSeek-V4 284B, Nemotron-30B) + RouteCrack 2.0.
Run Kimi K3 locally on CPU with ~55GB measured runtime RAM. A single-file Linux inference server powered by cPilot Runtime.
jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices, and scores with probabilities, on your laptop's CPU.
Spotted seal โ Phocinae-Largha-150M-v1: a 144.3M bilingual decision model. Tiny model. Big decisions. Little seal, big decisions.
Vui Nano โ a small, context-aware text-to-speech model trained on real conversations. 219M active parameters (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Includes a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.
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.
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
Frequently Asked Questions
What is the most popular #cpu-inference repository on GitHub?
The top ranked open source #cpu-inference project on GitHub is microsoft/BitNet with 42,358 stars. Official inference framework for 1-bit LLMs
Which programming languages are most used in #cpu-inference repositories?
Among the top ranked #cpu-inference projects on GitHub, the most common programming languages are Python, C++, C, HTML.
How is the #cpu-inference repository ranking calculated?
We track 17 active open source repositories tagged with #cpu-inference (500+ stars), totaling 84,398 stars with an average of 4,964 stars per repository. Rankings update daily from the GitHub API.