Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
BotPsy-0.8B-GGUFs
Modelstext generation model by qvac · gguf
qvac/BotPsy-0.8B-GGUFs -
image text to text model by Mia-AiLab · exllamav3
Mia-AiLab/DeepSeek-V4.1-Flash-1017-EXL3-EAQ-v1-2.9-bpw -
text generation model by nota-ai · mlx
nota-ai/Nemotron-3.5-Lightning-30B-A3B-Nota-Ternary-MLX-1014 -
text generation model by abenzerps · gguf
abenzerps/Spark-X2.6-4B-Uncensored-GSQ-RCO-GGUF -
image text to text model by SC117 · gguf
SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF -
modern-llm-notebook
Docs & tutorialsA hands-on course on modern LLM architectures, training, and inference, with step-by-step PyTorch implementations and runnable notebooks.
git clone https://github.com/walkinglabs/modern-llm-notebook.git -
Kimi-K3.1-Pro-NVFP4
Modelsimage text to text model by nvidia · Model Optimizer
nvidia/Kimi-K3.1-Pro-NVFP4 -
image text to video model by BennyDaBall · minimax-h3
BennyDaBall/HyperFlow-H3-Flash-INT8-ComfyUI -
project-maya
AI repositoriesProject Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
git clone https://github.com/mw00/project-maya.git -
llama-modchip
Agents & frameworksRun 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
git clone https://github.com/synchopate/llama-modchip.git -
Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInfer
Modelsimage text to text model by nerkyor · ninfer
nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInfer -
nemotron-3.5-120b-cq
Modelsimage text to text model by Cactus-Compute · mlx
Cactus-Compute/nemotron-3.5-120b-cq -
Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF
Modelsimage text to text model by DavidAU
DavidAU/Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF -
janas
AI repositories37 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.
git clone https://github.com/prabanta-dev/janas.git -
ARIS-in-AI-Offer
AI repositoriesBilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱
git clone https://github.com/wanshuiyin/ARIS-in-AI-Offer.git -
deepseek-local-guide-ru
Docs & tutorials🐋 Полный гайд на русском: как установить и запустить DeepSeek локально (V4, R1) на ПК, Mac и сервере — Ollama, llama.cpp, LM Studio, vLLM, Open WebUI, API, RAG, агенты, fine-tuning, лучшие фишки
git clone https://github.com/justxor/deepseek-local-guide-ru.git -
taOS
Agents & frameworksSelf-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).
git clone https://github.com/jaylfc/taOS.git -
image text to text model by DavidAU
DavidAU/Qwen3.8-Flash-Next-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF -
gguf-mcp
MCP serversInspect local GGUF/safetensors models: quantization, params, VRAM fit — headers only.
gguf-mcp@0.1.1 -
BigMoeOnEdge
AI repositoriesRun MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
git clone https://github.com/Helldez/BigMoeOnEdge.git -
agent-mosaic-skill
MCP serversConvert photos to LEGO-style brick mosaic previews with AI-powered color quantization.
@bmbrick/agent-mosaic-skill@1.0.2 -
imp
Agents & frameworksRun large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.
git clone https://github.com/kekzl/imp.git -
z-image-studio
MCP serversA Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)
git clone https://github.com/iconben/z-image-studio.git -
apple-silicon-llm-bench
Datasets & benchmarksReproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the same model and harness, every number with its quantization and capture session; hybrid Mamba-2 models (Nemotron-3 Nano, Granite-4.0-H, Falcon-H1) included.
git clone https://github.com/john-rocky/apple-silicon-llm-bench.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.