NVIDIA released two open MoE vision models, Nemotron-3.5-Bolt (74B-A9B) and Nemotron-3.5-Super-VL (120B-A12B), according to Unsloth AI. Unsloth says Bolt GGUF runs on 24GB RAM and Super-VL on 82GB RAM, and it links GGUF files and a guide for each.
The post gives memory requirements and GGUF links for both models, showing which hardware can run each one locally.
NVIDIA releases 2 new models: Nemotron-3.5-Bolt and Nemotron-3.5-Super-VL.
Nemotron-3.5-Bolt-74B-A9B runs on 24GB RAM. It delivers top-tier performance for its size.
Super-VL-120B-A12B runs on 82GB RAM.
Bolt GGUF: https://huggingface.co/unsloth/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-GGUF
Guide: https://unsloth.ai/docs/models/nemotron-3.5-bolt
Super GGUF: https://huggingface.co/unsloth/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF
Meet NVIDIA Nemotron 3.5 Super VL Our new open model combines reasoning and tool use with text, image, document, and video understanding for long-running AI agents. 120B total parameters with 12B active 🧵
Source: Unsloth AI · x.comPublished · added here
