nemotron-nano-12b-v2-vl-free · Nvidia
Developed by Nvidia, Nemotron-Nano-12B-V2-VL-Free is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It features a powerful 128,000-token context length to handle extensive visual and textual inputs. The model utilizes a hybrid Transformer-Mamba architecture, successfully combining transformer-level accuracy with Mamba's structural advantages.
Developed by Nvidia, Nemotron-Nano-12B-V2-VL-Free is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It features a powerful 128,000-token context length to handle extensive visual and textual inputs. The model utilizes a hybrid Transformer-Mamba architecture, successfully combining transformer-level accuracy with Mamba's structural advantages.
Nemotron Nano 12B V2 VL (free) has a 131,072 token context window.
Nemotron Nano 12B V2 VL (free) accepts text, image and video input.
Nemotron Nano 12B V2 VL (free) supports reasoning, tool calling and long context. Per-protocol parameter support is listed in the capability table on this page.
Nemotron Nano 12B V2 VL (free) is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to nemotron-nano-12b-v2-vl-free — no other code changes needed.
Nemotron Nano 12B V2 VL (free) is developed by Nvidia. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Nemotron Nano 12B V2 VL (free) was released on October 28, 2025 by Nvidia.
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, featuring…
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, featuring…
NVIDIA-Nemotron-Nano-9B-v2-free is a large language model trained from scratch by NVIDIA…
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model built on a hybrid…
Developed by Nvidia, NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model…
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model featuring…
Use Nemotron Nano 12B V2 VL (free) via the AIHubMix unified API — one interface for every major LLM.