Alternatives to Picollm

Run GGUF language models offline on your Android phone via llama.cpp, with all data staying on-device.

Run LLMs, speech-to-text, and image generation fully offline on your device via a Kotlin Multiplatform library, an app, and an IDE plugin.

Microsoft's MIT-licensed inference framework that runs 1-bit (ternary) BitNet b1.58 LLMs losslessly on CPU and GPU — no GPU required.

Ollama runs open-weight LLMs locally or in the cloud — unlimited local inference, per-token cloud pricing.

On-device GenAI SDK for Qualcomm Snapdragon — now folded into Qualcomm AI Hub.

Free, MIT-licensed local LLM inference for Apple Silicon Macs, with SSD-backed prefix caching and native OpenAI and Anthropic APIs.

Run Llama 3.1 405B and other huge language models at home over a BitTorrent-style decentralized inference network

Enclave runs open-source AI models entirely on your iPhone or Mac, so your chats, voice notes, and PDFs never leave the device.

Free on-device text-to-speech that runs locally via ONNX Runtime — no per-character cloud bill.

Typeahead is a native macOS app that finishes your sentences inline in every app you type in — running fully on-device for a one-time $79.

On-device multimodal AI SDK for iOS and Android, now integrated into Qualcomm AI Hub after Nexa AI's acquisition.

On-device Mac autocomplete that predicts your next words inline in any app and never sends your text to the cloud.

Free, open-source desktop app to run 123 HuggingFace models locally or route prompts to Claude, GPT, Gemini and DeepSeek with your own API keys

Free local RAG chatbot from NVIDIA that answers questions over your own files on an RTX Windows PC

LM Studio runs open-source LLMs locally on your own machine, with Bionic as its agent for coding, documents, and automation.

Free, open-source desktop app for running and fine-tuning RWKV RNN language models locally with infinite context.

LLM Hub runs 15+ AI models — chat, image, video, music, code — entirely on your Android or iOS phone, with no cloud and no account.

Free open-source local AI server that runs LLMs, image, music, video, and 3D generation on your own Apple Silicon Mac.

Run any GGUF AI model locally on Android with zero network permissions

Atomic Chat is a free, open-source desktop and mobile AI app that runs 1,000+ local LLMs on your own hardware, with no account and no rate limits.

Open-source, local-first desktop AI client that connects to multiple model providers and keeps your data on your machine.

Liquid AI's open-weight LFM2.5 model family runs native text, vision, and audio AI locally on CPU, GPU, or NPU.

Mesh LLM shards giant open-weight models across the GPUs you already own and serves them from one local OpenAI-compatible endpoint at localhost:9337.

Open-source on-premise RAG framework from the team behind Zylon — 57k GitHub stars, 100% local document Q&A.

Locally-run AI friend that rebuilds a real person's tone from your exported QQ and WeChat chat history

Free desktop AI that runs the Mistral 7B model locally so your documents never leave your machine.

Open-source repo of pre-converted .aimodel bundles and recipes for Apple Core AI on iOS 27 and macOS 27.

Open-source MIT runtime that serves text, voice, vision, image, 3D and agent workloads through OpenAI, Anthropic, Ollama and ElevenLabs-compatible APIs on your

Open-source desktop client that puts your OpenAI, Azure, Google, and Replicate API keys behind one chat and image interface.

A headless React hooks library that runs a Vicuna-13B chat model entirely in your browser via WebGPU, with no server round-trip.