200 apps like PrismML, closest match first.
AI-Mizu
AI Mizu provides a platform to test and use multiple AI models in one interface
AI Stats
AI Stats provides a comprehensive database of AI models and updates
Gravity-AI
The fastest & most secure way to solve business problems with A.I
ai/gateway
One API for every frontier and open-weight model
LMRing
Open-source, self-hostable LLM arena
AIModels.fyi
Find the AI breakthroughs that actually matter
Nesa
Run AI models end-to-end encrypted
Matrixhub
An Open-source, self-hosted AI model hub
Locai
AI orchestration for open-weight models and frontier APIs
Prisca AI
No-code ML, data analytics, dashboarding platform for individuals and businesses
Coreai Model Zoo
Downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac
ClearML
Revolutionary AI model development and management platform optimizing workflows
modelpricelab
Track real-time pricing, deprecation notices
Janas
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs…
Admix
A mix of the best AI Models and Tools in one place
AIBoox
AIBoox delivers AI model access through globally distributed computing regions
Web LLM
High-performance In-browser LLM Inference Engine
Locally AI by LM Studio
Run AI models like Llama, Gemma, Qwen, and more on your iPhone and iPad
Kiln
Intuitive app to build your own AI models
Baidu PaddlePaddle
Develop adaptive AI solutions effortlessly, leverage GPU acceleration
TunemyAI
Optimize and deploy AI models effortlessly
ChatLLM-Web
Private local model studio, AI chat
mlx-serve
Native LLM inference server for Apple Silicon
TheWhisper
Optimized Whisper models for streaming and on-device use
PrismerCloud
Prismer Cloud
Mirai
Inference engine for AI models
PixelVerse t1
An advanced logical thinking and reasoning AI model
Envyon AI
Deploy powerful AI models on private, dedicated infrastructure
Quail
Local model server for GGUF and MLX models on Apple silicon
vllm-mlx
High-performance OpenAI and Anthropic compatible LLM inference server
MLX Tune
Fine-tune LLMs on your Mac with Apple Silicon
Benchable
Benchable lets you benchmark and compare over 300 AI models including GPT-4
BodhiApp
Run Open Source/Open Weight LLMs locally with OpenAI compatible APIs
llama.ui
A minimal interface for AI Companion that runs entirely in your browser
OMNY.CHAT
All-in-one AI workspace to access ALL premium models
CanIRun.ai
Check AI model hardware compatibility
NadirClaw
Source-available LLM router and AI cost optimizer
ToolNeuron
Encrypted & Privacy First, On Android Device AI App
pooled
Peer-to-peer LLM inference in the browser: pool your devices
ReasonBlocks
Specialized models that make your AI agents cheaper and more reliable
Netron
Visualizer for neural network and machine learning models
Efficient-LLMs-Survey
[TMLR 2024] Efficient Large Language Models: A Survey
Stellon Labs
Building tiny frontier AI models that run on edge devices
Prime Intellect
Train, deploy, and continuously improve your own models on an integrated
LM Studio
Agent for Work and Code
Bolt by Sparcle
Use any AI model without sending your secrets
Ling
The LLMs' framework optimized for ultra-fast response times
Modellix
All leading AI models. One API. Zero hassle
TurboLLM
Run any local LLM engine, auto-tuned to your GPU
AI//COST
Independent directory that tracks source-verified API pricing