Resources

Tools, frameworks, and models for local AI

All Organizations Hardware Software Models Inference Frameworks

Sort by:Name (A-Z)Name (Z-A)Category Newest first Oldest first Price (low to high)Price (high to low)VRAM (highest first)Parameters (largest first)

5 resources found for "NVIDIA"

Models

NVIDIA ARDY-Core-RP-20FPS-Horizon40

Released Jul 10, 2026Core-RP-20FPS-Horizon40

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.

motion-generationdiffusionroboticsanimation

Learn more

CompareSite

Models🧮

NVIDIA Kumo-Tabular

Released Oct 14, 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.

TabellareDatiOpen-weightsBusiness

Learn more

CompareSite

Models🗣️

NVIDIA MagpieTTS Multilingual 357M

Released Dec 1, 2025MagpieTTS Multilingual 357M

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.

TTSAudioMultilingueOpen Source

Learn more

CompareSite

Models📄

NVIDIA Nemotron Parse (famiglia OCR)

Released Jun 30, 20262.0

NVIDIA's vision encoder-decoder family for local document understanding: markdown, LaTeX formulas, bounding boxes and a semantic class per element, in reading order. ViT-H (C-RADIO) + 10-block mBART decoder, all under 1 billion parameters. Locally via vLLM (v0.20–v0.26 for 2.0) or Transformers, on NVIDIA GPUs (Turing through Blackwell).

OCRDocumentiNVIDIAOpen WeightVLM

Learn more

CompareSite

Models🎙️

NVIDIA NemotronLabs VoiceChat 11B

Released Aug 3, 202611B

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.

VocaleOpen SourceLocaleNVIDIA

Learn more

CompareSite