PromptQuorum: Your Discovery Engine for Open-Weight & Open-Source AI
Directory, Guides & Comparison Tools for Local LLMs
(in plain terms: running an AI model for free on your own computer)
Just published
Added in the last 3 days
- NewReview
Local AI Mail Review: Brand-New Android Email Client with an On-Device AI
Local AI Mail review: a very early Android email client that summarizes, translates and drafts replies with on-device AI. 0+ downloads, untested.
October 11, 2026
- NewApp
Microsoft Agent Framework
Microsoft's unified SDK for AI agents and multi-agent workflows
October 10, 2026
- NewReview
Return Editor Review: Local-First AI Contract Review for Mac and Windows
Return Editor review: a desktop app for Mac and Windows with contract risk flags, cited answers and a free local AI. Privacy, pricing, limits.
October 10, 2026
- NewHands-on test
BoBe Alpha on a 24 GB Mac: Easy to Install, Restarted When Deleted
Hands-on test on a MacBook Pro with M3 Pro. The in-app assistant did not name the macOS setting it needs, and the app restarted itself when the tester tried to delete it.
October 9, 2026
- NewHands-on test
Draw Things on a 24 GB Mac: Fast When It Works, Blind Until It Does
Hands-on test on a MacBook Pro with M3 Pro. The first prompt returned a gray square. The second model worked.
October 9, 2026
- NewReview
FriedrichAI Review: Offline Windows AI Assistant Sold on Steam
FriedrichAI review: a paid offline AI assistant for Windows sold on Steam, with local memory, image/video/audio packs, no account. Hardware, privacy, limits.
October 9, 2026
- Apps tracked
- 241
- Languages
- 9
- Apps verified by their makers
- 9
- Articles published
- 809
- Apps tested hands-on
- 3
- AI assistant calls (MCP)
- 1,519
Open directory →
The makers confirm the information presented about their apps.
PromptQuorum has installed and tested the software itself.
See how AI assistants use this site →
Find What You Need
Pick what you're after, then search.
Largest local LLM app directory outside GitHubBrowse 241 apps →Compare Tools
Pick a category, choose up to three tools, and see them side by side. Copy the table or open the full guide.
Pick a category above to start comparing.
Optimize one prompt. Ask 25+ AIs. Compare the answers.
PromptQuorum structures your prompt, sends it to many models at once, and shows where they agree.
- Automatic prompt optimization
- One prompt to 25+ AI models
- Side-by-side comparison
- Consensus scoring
- Local LLM support
Local AI Tools
Four ways to match your hardware to the right software.
VRAM Calculator
Work out how much VRAM a model needs before you download it.
Open the calculator →
What Can I Run?
Enter your hardware, get local-AI apps that fit.
Find compatible apps →
Can I Run This?
Pick an app, check it against your hardware.
Check an app →
Connect via MCP
Let Claude, ChatGPT, or any MCP client query this directory directly. Setup, tools, and live usage stats.
Set up MCP →
Latest Posts
- New
Local AI Mail Review: Brand-New Android Email Client with an On-Device AI
Local AI Mail review: a very early Android email client that summarizes, translates and drafts replies with on-device AI. 0+ downloads, untested.
October 11, 2026
- New
Return Editor Review: Local-First AI Contract Review for Mac and Windows
Return Editor review: a desktop app for Mac and Windows with contract risk flags, cited answers and a free local AI. Privacy, pricing, limits.
October 10, 2026
- New
Local AI: Offline Chat & Image Review: Free Android App with Stable Diffusion and Prompt Toolkits
Local AI: Offline Chat & Image review: a free Android app with 20+ offline models, Stable Diffusion images and 15 prompt toolkits. Ads, privacy and limits.
October 9, 2026
- New
FriedrichAI Review: Offline Windows AI Assistant Sold on Steam
FriedrichAI review: a paid offline AI assistant for Windows sold on Steam, with local memory, image/video/audio packs, no account. Hardware, privacy, limits.
October 9, 2026
- New
BoBe Alpha on a 24 GB Mac: Easy to Install, Restarted When Deleted
Hands-on test on a MacBook Pro with M3 Pro. The in-app assistant did not name the macOS setting it needs, and the app restarted itself when the tester tried to delete it.
October 9, 2026
- New
Draw Things on a 24 GB Mac: Fast When It Works, Blind Until It Does
Hands-on test on a MacBook Pro with M3 Pro. The first prompt returned a gray square. The second model worked.
October 9, 2026
- New
Page Assist on a 24 GB Mac: Sidebar Found, Page Not Understood
Hands-on test of the Ollama-based browser extension on an M3 Pro Mac. The toolbar icon opened a full-screen page instead of a sidebar. Once the sidebar was found, it counted words but did not read a Search Console page or act on a page.
October 9, 2026
MLXHub Review: On-Device MLX Chat and LAN Server for iPhone and iPad
MLXHub review: iPhone and iPad app for on-device MLX models with an OpenAI-compatible LAN server and multi-device model splitting. Pricing, iOS 26 and RAM requirements, privacy, limits.
October 5, 2026
Oscilla Review: Free On-Device AI Chat for iPhone
Oscilla review: free iPhone app that runs 40+ open models (Gemma 4, Qwen 3, Granite) on-device with voice, memory and image input. Requirements, privacy label, limits, and alternatives.
October 4, 2026
Tina Review: iPhone Client for Ollama, llama.cpp and ComfyUI
Tina review: iPhone and Mac client for your own Ollama, llama.cpp and ComfyUI servers plus on-device models. Pricing, iOS 26 requirement, privacy label, limits, and alternatives.
October 4, 2026
Latest Apps Added
- New
Local AI Mail
Very early Android email client that summarizes, translates and drafts replies with an on-device AI, with optional Gemini cloud AI on your own key — Personal assistants
October 11, 2026
- New
Microsoft Agent Framework
Microsoft's unified SDK for AI agents and multi-agent workflows — Agent frameworks
October 10, 2026
- New
Return Editor
Desktop document editor for contract review: clause-level risk flags, cited answers and local semantic search, with a bundled local AI — Contract review
October 10, 2026
- New
FriedrichAI
Offline Windows AI assistant sold on Steam, with local memory, image/video/audio packs and no account — General chat clients
October 9, 2026
- New
Local AI: Offline Chat & Image (GeetMark)
Free Android app for offline chat with 20+ models, Stable Diffusion images and 15 prompt toolkits — General chat clients
October 9, 2026
MLXHub
On-device MLX chat for iPhone and iPad, with a LAN server and multi-device model splitting — General chat clients
October 5, 2026
Oscilla
Free iPhone app that runs 40+ open models fully on-device, with voice and memory — General chat clients
October 4, 2026
Tina
iPhone/Mac client for your own Ollama, llama.cpp and ComfyUI servers, plus on-device models — General chat clients
October 4, 2026
AquaVoice
Cloud voice dictation that types into the active app, for AI prompts and messages — Speech-to-text
October 3, 2026
Private Mind
Open-source, offline AI chat for iPhone and Android, with on-device document Q&A — General chat clients
October 3, 2026
Latest Founder/Maker Reviews
- New
FriedrichAI
Randolph Smith, solo developer — FriedrichAI started almost by accident. I'm a longtime software QA guy, not an AI researcher. Local AI was incredibly interesting, but getting everything installed, configured and working could be a project in itself. So FriedrichAI gradually became an attempt to package that experience into something normal people could actually use.
October 9, 2026
PAIOS
Puzzak, developer — PAIOS is a pet project: a chat client for Gemini Nano that runs on the phone through Google AI Core. It first launched as "Gemini Nano" and gathered over 5,000 native installs in two days before Google removed the listing for impersonation.
October 5, 2026
TokForge
Isaac Maple, developer — So that's why I built it. I figure AI inference costs will keep going up and become more expensive for regular people to access AI they own, on their own devices, that isn't filtered or censored. So I wanted to make something that addressed that and was fast, free and without ads.
October 5, 2026
HilbertRaum
Vladimir Tosovic, HilbertraumAI — We want to make local AI as easy as possible — without having to deal with runtimes, quantization, or model files. In the best case, you just plug in a USB stick and get started.
September 25, 2026
Atlarix
Amariah Abishai, Founder, Norah Labs — Built Atlarix to be an AI coding agent trustworthy with a real codebase: one that plans, edits, runs the project's own tests, and never changes a file until the diff is approved — fully local when paired with Ollama or LM Studio.
September 25, 2026
Locally Uncensored
David, developer, LU Labs — My own local AI setup was a terminal running Ollama and a row of ComfyUI tabs, and every task meant switching between them. I wanted one installer that puts chat, a coding agent, image, video, and LoRA training on one screen, on my own PC, with nothing leaving it.
September 22, 2026
Cherry Studio
Seth, Cherry Studio Team — All they should need to say is "Help me get this done," and the Agent will automatically decide whether to query the knowledge base, trigger OCR, generate an image, process a file, or write a note.
September 20, 2026
Pocket AI
Faisal, developer — Every good local-model app on iPhone asked for an account, a subscription, or a server round trip first. Pocket AI runs entirely on-device via llama.cpp with Metal acceleration — no account, no server.
September 13, 2026
Loci AI
September 5, 2026
Latest Hands-on Tests
- New
Draw Things on a 24 GB Mac: Fast When It Works, Blind Until It Does
Hands-on test on a MacBook Pro with M3 Pro. The first prompt returned a gray square. The second model worked.
October 9, 2026
- New
BoBe Alpha on a 24 GB Mac: Easy to Install, Restarted When Deleted
Hands-on test on a MacBook Pro with M3 Pro. The in-app assistant did not name the macOS setting it needs, and the app restarted itself when the tester tried to delete it.
October 9, 2026
- New
Page Assist on a 24 GB Mac: Sidebar Found, Page Not Understood
Hands-on test of the Ollama-based browser extension on an M3 Pro Mac. The toolbar icon opened a full-screen page instead of a sidebar. Once the sidebar was found, it counted words but did not read a Search Console page or act on a page.
October 9, 2026
Trending / Most-Read
Snapshot as of October 4, 2026 (last 28 days)
- Uncensored Local LLMs for Creative Writing
4,218 clicks - 無検閲ローカルLLMと創作活動
1,918 clicks - 无审查本地LLM与创意写作
1,194 clicks - 로컬 LLM 순위·추천: VRAM 등급별 비교
790 clicks - Best Local LLM Apps for Android679 clicks
- Small Local LLM Models648 clicks
- Fastest Local LLMs for Low-End PCs570 clicks
- Beste lokale LLMs im Vergleich
563 clicks - Best CPU-Only LLM552 clicks
- Apple MLX vs. NVIDIA CUDA for Local LLMs548 clicks
- Best AMD Mini PC for Local LLMs491 clicks
- iPhoneで使えるLocal LLMアプリ比較458 clicks
- Best Local LLMs by VRAM Tier424 clicks
- コーディング用ローカルLLM：Kimi K2.6 vs Qwen vs Devstral421 clicks
- Local LLM Hardware Guide406 clicks
- 창의적 글쓰기를 위한 무검열 로컬 LLM370 clicks
- Apple Silicon M5 for Local LLMs364 clicks
- 로컬 AI와 로컬 LLM이란?348 clicks
- Best Local LLMs for Coding334 clicks
- Best AMD GPUs for Local LLMs327 clicks
Recently Updated Content
- Updated
Apple Silicon for Local LLM 2026: M5 Pro vs M5 Max vs Mac Studio Compared
Updated October 11, 2026
- Updated
The Complete Local AI & LLM Software Directory: 241 Apps & Tools for Running AI Locally (2026)
Updated October 11, 2026
- Updated
Nanobot Review: A Self-Hosted AI Agent Framework in 2026
Updated October 10, 2026
- Updated
Open WebUI in 2026: The Self-Hosted ChatGPT Interface for Ollama and Any AI Model
Updated October 9, 2026
- Updated
Enterprise RAG Vector Database Deployment: Self-Hosted vs Managed (2026)
Updated October 9, 2026
- Updated
Draw Things Review: Local-First Image AI with Optional Cloud
Updated October 9, 2026
- Updated
KoboldCpp Review: One File, No Install, Built for Roleplay
Updated October 9, 2026
- Updated
Windsurf Review: From Codeium to a $2.4B Google Deal to Devin Desktop
Updated October 9, 2026
- Updated
SwarmUI Review: The Multi-GPU Stable Diffusion Web UI
Updated October 9, 2026
- Updated
TokForge Review: Offline Android AI Chat with Roleplay and Image Generation
Updated October 9, 2026
Recent Mentions
Most Recent
- Minisforum um890 pro META Preisvergleich — META PreisvergleichOctober 4, 2026 · DR 36
- IFA 2026: AMD के लोकल AI PC में लैपटॉप से 192GB मेमोरी वाले NAS तक विकल्प — Studio Global AI
October 4, 2026 · DR 29 - OpenAI được cho là mua hàng chục nghìn máy Mac: Không phải để thay thế các cụm GPU Nvidia — Studio Global AI
October 4, 2026 · DR 29 - ทางสายกลางของ AI ยุคใหม่: ใช้โมเดลจีน Self-Host เพื่อควบคุมข้อมูล หรือเช่า API สหรัฐฯ เพื่อความง่าย — Studio Global AI
October 4, 2026 · DR 29 - Локальные LLM на Android: что и зачем реально можно гонять на телефоне — Hermes Agent
October 4, 2026 · DR 21 - Home Assistant 完整教學 2026：9 萬星開源智慧家庭中樞，HAOS／Docker 安裝、Zigbee 與 Matter 設定 — Dennis 技術視野洞察
October 4, 2026 · DR 11 - Muss ich wirklich Prompt Engineering lernen? — KI einfach nutzen — better-computing.comOctober 4, 2026 · DR 6
- Workstation AI vs DGX Spark — Supercat.dev
October 4, 2026 · DR 0 - AnythingLLM — Grokipedia article — GrokipediaOctober 2, 2026 · DR 79
- 192GB统一内存加持，消费级硬件单台能跑2840亿参数大模型 — SMZDMOctober 2, 2026 · DR 79
What's your biggest local LLM headache?
Are you a founder? Tell us about your app →Did You Know?
little-coder defaults to a locally served Qwen3.6-35B-A3B model running over llama.cpp, tuned specifically to get good results from smaller local models.
Read more: little-coder Review →