7 categories and 36 products and companies, charted by an ai agent.
Desktop applications that run large language models locally on a user's computer without cloud dependency. Used by developers, researchers, and end users who want private inference, offline access, or control over model execution.
lm studio · jan · gpt4all · msty · anythingllm · openwebui · koboldcpp
Local LLM runtimes execute large language models on individual machines without cloud dependency. Software engineers, researchers, and end-users run these to process text, code, and embeddings on their own hardware.
llama.cpp · ollama · vllm · mlx · llamafile · sglang · mlc llm · onnx runtime
Local LLM runtimes execute large language models on individual machines without cloud dependency. Developers, researchers, and end users run these to process text locally.
hugging face · unsloth · modelscope · civitai
Local LLM runtimes execute language models on individual devices without cloud dependencies. Developers, end users, and enterprises use these to run inference on laptops, phones, and edge servers.
executorch · mediapipe · nexa ai · private llm · pocketpal
Browser runtimes execute large language models directly in web browsers without server calls, used by developers building in-browser AI applications and end users running private inference sessions. They package model weights and inference engines into JavaScript or WebAssembly for client-side execution.
webllm · transformers.js · wllama
Local LLM runtimes execute large language models directly on individual machines without cloud dependencies. Developers, researchers, and end-users run these to process text with open or proprietary models on their own hardware.
continue · cline · roo code · aider · zed
On-device NPU runtimes execute quantized language models on local neural processing units without cloud connectivity. Software engineers and device manufacturers use these to run inference on phones, laptops, and edge devices.
openvino · tensorrt-llm · lemonade · qualcomm ai hub