Local AI for Low-End PCs and Laptops

Find local AI apps with CPU modes or support for modest PC hardware: small-model chat, dictation, OCR and translation. Check RAM and graphics requirements.

20 tools
Favicon of koboldcpp

koboldcpp

4 videos
A local LLM runner for GGUF models on Windows, macOS and Linux, with CPU or GPU support and a browser interface for chat and roleplay.

12.3KUpdated 2 weeks agoAGPL-3.0

macOS · Windows · Linux · Android · Docker · Web#GGUF#Hugging Face integration#llama.cpp backend

An offline speech-to-text app runs on Windows, macOS and Linux with CPU-only transcription, custom vocabulary and optional local or remote LLM rewriting.

1.2KUpdated 1 day agoAGPL-3.0

macOS · Windows · Linux#Multilingual#Wake word detection#Works offline

A free browser translator translates pages and subtitles in Chrome and Firefox, with offline processing and local backends such as Ollama.

1.1KUpdated 2 months agoBSD-3-Clause

Android · Browser Extension#Multilingual#Ollama integration#Works offline

An open-source OCR toolkit extracts text from images offline, with Chinese and English recognition and support for CPU and GPU inference.

8.5KUpdated 2 days agoApache-2.0

Docker#Multilingual#ONNX#Works offline

Favicon of GPT4All

GPT4All

2 videos
A local AI chatbot runs GGUF models and private document chat on Windows, macOS and Linux without requiring a GPU or cloud API.

77.3KUpdated 1 year agoMIT

macOS · Windows · Linux · Docker#GGUF#llama.cpp backend#OpenAI-compatible API

Free, open-source OCR software for Windows that extracts text from screenshots and image batches offline, with watermark exclusion and QR code tools.

48.7KUpdated 12 months agoMIT

Windows · Linux#Batch processing#Multilingual#Works offline

A local AI anime image upscaler runs on Windows, Linux and macOS, with adjustable denoising and support for Intel, AMD, NVIDIA and Apple Silicon GPUs.

931Updated 4 years agoMIT

macOS · Windows · Linux#Batch processing

A self-hosted AI web interface runs GGUF chat models and generates multimedia locally, with offline use after model downloads and CPU-only support.

1.2KUpdated 24 hours agoGPL-3.0

macOS · Windows · Linux · Docker · Web#ControlNet#GGUF#Image-to-image

An offline translation library and desktop app that runs locally, supports custom language models, and is open source under the MIT license.

6.7KUpdated 3 months agoMIT

Linux#Multilingual#Works offline

Local AI image manager that searches, tags and scores photos, with desktop and self-hosted options and two-way ComfyUI integration.

99Updated 3 days agoGPL-3.0

macOS · Windows · Linux · Docker · Web#Batch processing#Hugging Face integration#ONNX

Favicon of llamafile

llamafile

2 videos
A local LLM runner bundles a model and runtime into one executable that works across operating systems and CPU architectures without installation.

26.6KUpdated 1 week ago

macOS · Windows · Linux#GGUF#Hugging Face integration#llama.cpp backend

A free local AI image generator runs Stable Diffusion on Windows, Linux and macOS, with a browser interface for editing images and ControlNet guidance.

10.5KUpdated 4 weeks ago

macOS · Windows · Linux · Web#Batch processing#ControlNet#Image-to-image

A local text-to-speech toolkit generates speech with voice cloning, language-specific models and GGUF support on macOS, Windows and Linux.

6.3KUpdated 4 months ago

macOS · Windows · Linux#GGUF#Hugging Face integration#llama.cpp backend

A local AI upscaler for Windows that enlarges images, animations and video, adds intermediate video frames, and supports AMD, NVIDIA and Intel GPUs.

17.2KUpdated 4 days ago

Windows#Batch processing#Works offline

Favicon of Jan

Jan

5 videos
A free desktop ChatGPT alternative runs local models offline on Windows, macOS and Linux, or connects to cloud models such as GPT and Claude.

45.7KUpdated 2 days ago

macOS · Windows · Linux#Hugging Face integration#MCP#OpenAI-compatible API

Favicon of Ollama

Ollama

261 videos
An MIT-licensed local LLM runner and API for macOS, Windows, Linux and Docker, with optional cloud inference and coding agent integrations.

186.9KUpdated 21 hours agoMIT

macOS · Windows · Linux · Docker#GGUF#llama.cpp backend#Multimodal input

Favicon of Handy

Handy

9 videos
A free, open source offline dictation app for Windows, macOS and Linux that uses local Whisper or Parakeet models to enter text in desktop apps.

38.7KUpdated 2 days agoMIT

macOS · Windows · Linux#GGUF#Hugging Face integration#Voice activity detection

Favicon of KittenTTS

KittenTTS

1 video
A local text-to-speech library runs on CPU, clones voices from short recordings, and supports multilingual speech on Windows, macOS and Linux.

16.9KUpdated 2 days agoApache-2.0

macOS · Windows · Linux#GGUF#Hugging Face integration#llama.cpp backend

A local translation app runs Marian and Bergamot models on Windows, macOS and Linux, with desktop, command-line and browser extension access.

643Updated 2 years agoMIT

macOS · Windows · Linux · Web · Browser Extension#Batch processing#Multilingual#Quantization

An offline AI photo editor for Linux and Windows that adjusts people and backgrounds separately, keeps photos local and doesn't require a GPU.

63Updated 1 month agoLGPL-2.1

Windows · Linux#Works offline

Favicon of LogotyperLogotyper
Got an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.
Start your project
Favicon of Logotyper
Favicon of LogotyperLogotyper
Got an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.
Start your project
Favicon of Logotyper

What works on a modest PC?

CPU-based chat with a small quantized model, offline translation, OCR and dictation are useful starting points. Memory needs depend on the model and conversation length, so CPU support alone is not a promise that every model will fit. For GPT4All on a PC, the documented 8 GB minimum applies to small 3B models; choose downloads that fit your machine.

Check the exact edition and engine. Umi-OCR's Rapid edition supports older Windows CPUs that its Paddle edition does not. Some image upscalers can use compatible integrated graphics, including tested Intel GPUs, but still need that graphics support and may be slow. This collection includes CPU options and integrated-GPU options; it does not promise GPU-free operation for every app.