Tools, frameworks, and models for local AI
60 resources found for "Open Source"
The newest open music model with excellent control over lyrics and styles: generates complete songs with lyrics in many languages, including Italian.
27B reasoning model with ternary weights at 1.72 bits per weight, derived from Qwen3.8-27B with hybrid attention (~75% linear). In GGUF PTQ1_0 it takes 5.95 GB, retains 98.2% of the FP16 intelligence and reaches ~47 tok/s on an Apple M5 Max laptop, with a 262K-token context. Apache 2.0 license. Requires Prism ML's llama.cpp fork (ternary kernels are not in stock llama.cpp).
NVIDIA's Rust CLI for AI-assisted Linux kernel development, focused on local AI: patch validation, builds, boot and tests, designed for backporting patches to older kernels. It supports local back-ends (Claude, OpenCode, Codex) or OpenAI-compatible servers. Apache 2.0, led by Andrea Righi.
Cloudflare's 27B multimodal decision model (base Qwen3.8-27B): reads a state (text, JSON, images, video) and a schema of typed questions and returns a probability per option in a single pass, with no text generation. Jev and SystemOne API compatible.
The node-based visual workflow for diffusion models: the standard for SDXL, FLUX, video and audio. Maximum flexibility, from simple to professional pipelines.
DeepSeek's MoE model with 552B total parameters and 8-16B active per token. 1M-token context, MIT license: free commercial use. Built for online serving, too large for local use on a single PC.
Reimplementation of Whisper based on CTranslate2: up to 4 times faster than openai/whisper with the same accuracy and less memory. Supports 8-bit quantization on both CPU and GPU.
Google's open model family in 1B, 4B, 12B and 27B sizes. 128K-token context, 140+ supported languages and multimedia input (text and images). An excellent choice for RAG and long documents on consumer hardware.
La taglia 12B della famiglia Gemma 4 di Google: 11,95B dense, contesto 256K e multimodalità integrata senza encoder separati (testo+immagini+audio). Licenza Apache 2.0. In Q4_K_M occupa circa 7,4GB: il punto di equilibrio tra qualità e requisiti hardware per l'uso locale su 8-16GB.
Il modello MoE della famiglia Gemma 4: 25,2B di parametri totali con 3,8B attivi per token. Contesto 256K, input testo+immagini, oltre 140 lingue, Apache 2.0. In Q4_K_M pesa circa 16,8GB: la scelta per chi ha 24GB di VRAM e vuole qualità da modello grande con velocità da modello piccolo.
Compact model from Google's Gemma 4 family: 8B total parameters, of which 4.5B effective thanks to per-layer embeddings (PLE). 131K-token context, 140+ languages, text+image and audio input. The entry size of the Gemma 4 family for local use on 8-16GB.
Hugging Face's Python library for running the pipelines of generative models: image, video, and audio. The standard way to run models like Qwen-Image locally, with CUDA support and CPU offload for lower-memory GPUs.
The standard library for NLP and multimodal models, with thousands of pre-trained models.
82-million-parameter speech synthesis model on a VITS architecture, Apache-2.0 for the weights, with voices in dozens of languages and surprisingly high quality for its size. Runs efficiently on CPU alone.
Model for local agents and specialized applications, 1.73B parameters, tri-hybrid architecture (13 gated short convolutions, 5 sliding-window attention, 6 global attention). Explicit agentic post-training (harnesses like Hermes Agent, Pi, OpenClaw), 256K-token context, 16 languages including Italian, ~1GB of RAM at 4-bit. LFM Open License v1.0.
Meta's largest open model: closed-frontier quality but datacenter requirements. In practice it needs high-VRAM multi-GPU or the cloud.
Frontier-class open model with 131K-token context. Needs 48-80GB VRAM, a Mac with unified memory, or a multi-GPU setup.
The de-facto local workhorse: solid quality, 131K-token context and a huge GGUF quantization ecosystem. The standard choice for chat and assistants.
Small, fast model with up to 131K-token context. Ideal entry point for chat and summarization on modest hardware, great on phones and mini-PCs.
Open source framework for unified fine-tuning of 100+ LLMs and VLMs (Qwen, Llama, Mistral, Gemma): from full SFT to LoRA, QLoRA and DPO, with a built-in WebUI and startup from a single YAML file. The community's reference project (ACL 2024).
Open-source tool that estimates local model inference speed across 250+ hardware configurations (GPU, Mac, CPU): measured estimates from community benchmarks or derived from similar setups. Use it to choose hardware before buying.
Fast, open video generation: text or image to 768px video with good motion quality. One of the fastest open video models.
Open-source inference engine (Rust, YC S25) that compiles and tunes its kernels directly on the target hardware: Apple Silicon, NVIDIA, AMD or CPU. On open models it claims up to 2× the speed of llama.cpp. Also aimed at serving agents.
Fast, efficient 7B model, well-tuned for multilingual European tasks. Excellent instruction quality at a fraction of the cost of 13B+ models.
Mistral's largest open-weight model: natively multimodal MoE with 1 trillion total parameters, ~49B active per token (52B including embeddings and output), up to 1M-token context. Trained from scratch on 3,800 NVIDIA Grace Blackwell. Mistral Ecosystem Open-Weight License (a modified MIT): commercial use ok; a Model-as-a-Service business requires a separate commercial license.
Il primo 'modello unificato' di Mistral: dense da 128B che unisce instruction-following, reasoning e coding in un'unica serie di pesi, sostituendo Medium 3.1, Magistral e Devstral 2. Multimodale (testo+immagini), contesto 256K, ragionamento configurabile. Open weights con licenza Modified MIT: uso libero fino a una soglia di fatturato per le grandi aziende.
Il modello della linea Small di Mistral, ora MoE: 119B di parametri totali con 6,5B attivi per token (128 esperti, 4 attivi). Unifica instruct, reasoning e coding in un unico modello multimodale (testo+immagini) con contesto 256K. Licenza Apache 2.0.
Open-source proxy that intercepts and displays the contents of HTTPS requests in plaintext: the tool to verify what actually goes over the network from your local AI setup.
Eight 7B experts with two active per token: 47B total params with large-model reasoning at a fraction of the compute cost. An open-world classic.
Google's open-source (Apache 2.0) on-device GPU inference engine, successor to the TensorFlow Lite GPU delegate: tensor virtualization, stage-aware KV cache for prefill and decode, FP16/INT8/INT4. Backends: OpenCL (Android), Metal (Apple), WebGPU via Dawn (browser), OpenGL ES 3.1+. Integrates with LiteRT; in production on Chrome, YouTube, Photos and Meet.
Apple's machine learning framework for Apple Silicon: lazy arrays computed across unified CPU and GPU, with unified memory as an asset. The mlx-lm library brings LLM training, fine-tuning (LoRA/QLoRA) and inference directly to the Mac.
GTK4/libadwaita app for GNOME to chat with local models via Ollama, in Rust under GPLv3: it handles Ollama setup, models, and loading local documents and images.
Generates up to 30 seconds of music or sound effects from a text description. The open reference for music models: light and versatile.
Modello di sintesi vocale multilingue di NVIDIA: 357M parametri, 12 lingue (italiano e francese inclusi), architettura encoder-decoder transformer. Compatto e pensato per esecuzione in locale a bassa latenza; pesi disponibili su Hugging Face.
11B end-to-end full-duplex voice model: audio understanding and generation in a single architecture, without the cascaded ASR→LLM→TTS stack. First open full-duplex model with tool calling during conversation, ~450ms responses, interruptions, and natural turns.
Open source tool to run LLMs locally with simplicity.
Il modello di ragionamento open-weight di OpenAI: MoE con 21B di parametri totali e 3,6B attivi (32 esperti, top-4), contesto 128K e quantizzazione MXFP4 nativa. Licenza Apache 2.0: i pesi partono già quantizzati a 4 bit, senza passo di conversione. Sta in 16GB di VRAM e gira anche su RAM unificata o CPU.
9B smartphone agent (image-text-to-text) derived from Qwen3.5-9B and fine-tuned on OpenMobile-2 data: Android screenshots and native app tools. AndroidWorld Pass@1 79.9, MobileWorld 50.4; SPA-Bench rises from 31.9 to 59.6 after RL training. vLLM and SGLang support; the training environments (MobileGym++) and recipes are public. Apache 2.0 license.
Sintesi vocale in locale a bassa latenza basata su ONNX: genera parlato naturale da testo in tempo quasi reale, anche su CPU. Multilingue (italiano incluso) e facile da integrare nei pipeline: download del modello, una riga di comando. MIT.
Alibaba's 20B (MMDiT) image-generation model: excellent in-image text comprehension, precise editing, and an Apache 2.0 license. The base of the Qwen-Image family, of which 2.1 is the compact 7B variant.
7B open-weight model (32-layer DiT) that unifies text-to-image generation up to 2048x2048, editing with up to 10 reference images, and native RGBA transparency. Designed to run locally on 16GB+ VRAM; supported by diffusers and ComfyUI.
Ultra-compact 0.5B-parameter model. Runs on any hardware, even embedded: ideal for lightweight summarization and low-power local devices.
Clear step up in reasoning and instruction quality over 8B models. Excellent for coding, agents and structured writing on 16GB GPUs or Macs with 32GB RAM.
Near-70B quality at a fraction of the size: the sweet spot for advanced use. Excellent in Italian, code and reasoning. Needs 24GB+ VRAM.
3B-parameter model with excellent multilingual support, including Italian. Good balance of quality and hardware requirements for summarization and drafting.
The top open dense model of its class, with first-class multilingual support for Italian, French and other European languages. Needs 48-80GB setups.
Mixture-of-Experts model: 30B total params but only 3.3B active per token. Small-model speed with mid-size quality; the best speed/quality ratio in its class.
Il modello dense 8B della famiglia Qwen3: 8,19B di parametri, contesto nativo di 40K token (espandibile con YaRN) e ragionamento in modalità think/non-think attivabile per prompt. Licenza Apache 2.0. È il punto di equilibrio per l'uso locale su GPU da 8-12GB: in Q4_K_M occupa circa 5GB, lasciando spazio per contesto lungo.
Il modello dense multimodale della generazione Qwen3.8 di Alibaba: 27,78B di parametri, input testo+immagini+video e contesto nativo di 262K token. Licenza Apache 2.0. L'attenzione ibrida (DeltaNet lineare + GQA) riduce la KV cache di circa il 75% rispetto a un transformer standard: in Q4_K_M sta su una singola GPU da 24GB.
0.6B safety-moderation model with a token-level classifier for real-time monitoring during incremental generation. Three severity tiers (safe, controversial, unsafe) and 119 languages: small and local, ideal for filtering outputs without the cloud.
Open-source serving engine for LLMs with RadixAttention, continuous batching and first-class speculative decoding (MTP, EAGLE, draft models, ngram). Apache-2.0 license.
Up to 47 seconds of text-to-audio: high-quality music and sound effects. Excellent for local audio production and sound design.
The image-generation classic: fast, light, and with the largest LoRA/ControlNet ecosystem of all. Perfect for 6-8GB GPUs.
The current standard for photoreal and artistic images at 1024px. Better prompt adherence and more coherent composition than SD 1.5.
Turns an image into a short ~2s video clip. The entry point for local video generation; 16GB VRAM recommended.
The classic command-line tool for capturing network packets: the most direct way to see who is talking to the outside from your machine.
State-of-the-art open video model at 720p: professional-level motion quality and frame coherence. Needs 24GB+ VRAM.
Il modello di trascrizione di riferimento per l'IA locale: 809M di parametri, 99 lingue, licenza MIT. Versione distillata di Large-v3 con decoder ridotto da 32 a 4 layer: trascrive circa 8 volte più veloce con perdita di accuratezza trascurabile. Gira in tempo reale su una GPU consumer e anche solo su CPU.
Il port C/C++ ad alte prestazioni di Whisper: trascrizione vocale in locale ottimizzata per CPU e Apple Silicon, senza dipendenze da Python. Quantizzazione GGML (Q4_0–Q8_0) con riduzione fino al 65% a disco, streaming via whisper-stream, accelerazione Metal/Vulkan. MIT.
The graphical tool for capturing and analyzing network traffic: filters, colors, statistics and real-time visualization of every connection.
