Tools, frameworks, and models for local AI
13 resources found for "Generazione"
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.
Very few steps, high quality, and strong text rendering. The distilled FLUX variant, built for speed.
Kandinsky Lab's foundation models for synchronized video and audio generation: from a prompt they generate video clips with aligned audio, released as open weights. Top paper of the day on Hugging Face (2026-10-06), with checkpoints and Spaces already available.
Fast, open video generation: text or image to 768px video with good motion quality. One of the fastest open video models.
326M-parameter autoregressive diffusion model for interactive real-time humanoid motion: online text prompts, kinematic constraints (root trajectories, keyframes, sparse poses) and sequences up to 8 seconds. Trained on Bones Rigplay 1 (27-joint Core skeleton, 20 fps), optimized for NVIDIA Ampere, Hopper and Blackwell GPUs. NVIDIA Open Model Agreement license, commercial use allowed. On Hugging Face since October 7, 2026.
A 500-million-parameter foundation model from NVIDIA for tabular data: prediction, imputation and generation on structured datasets, with OpenMDW 1.1 support and ready-to-use checkpoints. An example of local AI on business data, not text generation.
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.
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.
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.
The image-generation classic: fast, light, and with the largest LoRA/ControlNet ecosystem of all. Perfect for 6-8GB GPUs.
Turns an image into a short ~2s video clip. The entry point for local video generation; 16GB VRAM recommended.
