Trending local LLM tools

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.

The next-generation Markdown editor, with an AI writing assistant. Free and open source for macOS, Windows and Linux.

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch). No cloud, no API key.

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.

A self-hosted job search app that writes tailored resumes and cover letters from your profile.

Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.

BINNY: an open source agent harness for reverse engineering. Plug in any model, or a local one.

The next-generation Markdown editor, with an AI writing assistant. Free and open source for macOS, Windows and Linux.

Breakout week (~1 a week)

Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.

38× its usual pace (~9 a week)

Feel how fast a local LLM runs before you buy the hardware

after quiet weeks

37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.

11× its usual pace (~14 a week)

Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts

10× its usual pace (~19 a week)

Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images

16× its usual pace (~5 a week)

Run the DeepSeek Harness AI agent natively on Android — no root, no Termux, extension center included | 手机本地运行 DeepSeek Agent，免 Root 免 Termux

13× its usual pace (~5 a week)

LLM frontend for creative writing and roleplay

28× its usual pace (~2 a week)