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.
- avx2
- c99
- cpu-inference
- deep-learning
111,803 visible repositories in the index
241–264 of 2,854 · Most stars
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.
An open-source, tool-augmented conversational language model from Fudan University
BISHENG is an open-source enterprise Agent platform for building, deploying, and managing AI applications. It combines AI agents, workflows, RAG and knowledge management, desktop agent integration, and vibecoding app hosting with unified model management, evaluation, observability, access control, and enterprise administration.
AI Observability & Evaluation
Retrieval and Retrieval-augmented LLMs
KoboldCpp - Run GGUF AI models locally with a KoboldAI UI. One File. Zero Install.
A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
Translated100+ Chinese Word Vectors
OCR & Document Extraction using vision models
Device-native foundation models: 145B on a laptop, 35B on a phone. Latent MoE, SSD-streamed weights, a router that predicts loads a step ahead. Mac, iPhone, Android, Windows.
The Open Runtime for AI Agents
MiniCPM5: SOTA on-device LLMs, small yet powerful.
Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn
Ekko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.
Low-code framework for building custom LLMs, neural networks, and other AI models
Neovim plugin for GitHub Copilot
TranslatedA Codex jailbreak prompt and test pack for gpt.
free online AI resume editor,the only official website is https://magicv.art
Official JavaScript / TypeScript library for the OpenAI API
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
Layout-aware document engine for AI and a feature-rich Python toolkit for extracting, rendering and editing PDFs and other documents. Since version 2.0, its ML-based layout analysis turns PDFs and Office files into high-quality Markdown for RAG and agents, running fast on CPU and grounding every result to its source page.
Kimi K2 is the large language model series developed by Moonshot AI team
QLoRA: Efficient Finetuning of Quantized LLMs