gguf-models 开源项目推荐（89 个）

LeanBitLab /LeanType

LeanType是一款开源键盘，是HeliBoard的分支，具有额外功能和定制功能

pollockjj /ComfyUI-MultiGPU

这个 ComfyUI custom_node为任何 UNet 和 CLIP 加载器添加了一键“虚拟显存”功能，同时支持 WanVideoWrapper 的多GPU集成，管理层层的卸载/块切换到 DRAM *或* 显存，最大化显卡的潜在空间。还包括直接加载整个组件（UNet、CLIP、VAE）到你选择的设备上的节点

local-ai-zone /local-ai-zone.github.io

My public AI learning journey — sharing what I learn, build, test, and discover across AI. Traffic: 7K+ monthly clicks · 150K+ AI citations/month · 5.5 average search position across search engines. local-ai-zone.github.io

ashioyajotham /fingpt_trader

A quant trading system platform based on FinGPT, demonstrating new applications of large pre-trained Language Models in quantitative finance.

Sandipan006 /lokalmind-app

On-device AI chat for iOS. Private, offline-first. Runs open-weight LLMs via llama.rn with semantic memory - no cloud, no API keys

Belluxx /Perplex

Inspect LLM's logprobs and perplexity over a piece of text, or compare two LLMs (like a git diff)

controlecidadao /samantha_ia

Experimental interface environment for open source LLM, designed to democratize the use of AI. Powered by llama-cpp, llama-cpp-python and Gradio.

dieharders /obrew-studio-server

Obrew Server: A self-hostable machine learning engine. Build agents and schedule workflows private to you.

Ankit-ku-panda /Portable-USB-AI

Portable offline AI assistant powered by llama.cpp and GGUF models. Run a private local chatbot directly from a USB drive on Windows with no cloud, telemetry, or internet required.

Coaade-Inc /strataflow

Run very large MoE models (100B–1T+) on the hardware you already own, by streaming experts across VRAM/RAM/SSD. Source-available, free for personal use.

HelpingAI /inferno

Run Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1, and other state-of-the-art language models locally with scorching-fast performance. Inferno provides an intuitive CLI and an OpenAI/Ollama-compatible API, putting the inferno of AI innovation directly in your hands.

hrithickcodesai /ShellVibe

Your terminal's AI co-pilot. Describe your intent and get the command.

pradeepgudipati /gguf-switchboard

Run GGUF through llama.cpp and SafeTensors through vLLM behind one OpenAI-compatible endpoint. Your coding tools select a model; the switchboard manages the local runtime, process, and resident-model change.

ariannamethod /yent

YENT: You. Exist. No. Translation.

Ton-Llop /Jaull

Find LLMs that fit your hardware and validate them with reproducible local tests.

ariannamethod /doe

DoE Janus Architecture: Democracy of Experts

magomedcoder /gogguf

Running GGUF-Format ML Models in Pure Go

Fatrocu /Fatrocu

Fatrocu converts your e-archive invoices, cash register receipts, and receipts into Excel format within minutes using a 100% locally running AI, drastically reducing manual data entry.

arseniy0924 /rpc_manager

Web UI for orchestrating distributed llama.cpp RPC GPU clusters with auto node discovery, telemetry, and one-click deployment.

suraj-yadav0 /utgpt

An offline AI chat application built specifically for Ubuntu Touch, allowing users to run lightweight Large Language Models (LLMs) directly on their mobile device.