Documentation Navigation
Models & pricing / Models / NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 Overview
This model's data has not been fully verified and benchmarks may be missing.
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a chat-reasoning AI model created by nvidia, featuring 17.8B parameters and a context window of unknown.
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a 17.8B-parameter Mixture-of-Experts (MoE) text generation model developed by nvidia. Built on the NemotronHForCausalLM architecture using transformers. Supports en, es, fr, de, it, ja language(s). Released on 2026-08-04 with 194 likes and 19,250 downloads on Hugging Face.
Model Lineage & Specification
nvidia-nemotron-35-lightning-30b-a3b-nvfp4 is nvidia's primary release in the current family.
nvidia-nemotron-35-lightning-30b-a3b-nvfp4Comparable models
| Feature | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 | Solar Pro 4 | Qwen3.8 Max Preview | Nemotron 3 Ultra |
|---|---|---|---|---|
| Description | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a 17.8B-parameter Mixture-of-Expe... | Solar Pro 4 is a large language model from Upstage built for enterprise workflow... | Preview Qwen flagship for million-token multimodal reasoning and long-horizon ag... | NVIDIA Nemotron 3 Ultra is a flagship open-weight frontier LLM family engineered... |
| API Identifier | nvidia-nemotron-35-lightning-30b-a3b-nvfp4 | upstage-solar-pro-4 | alibaba-qwen3.8-max-preview | nvidia-nemotron-3-ultra |
| Parameters | 17.8B | — | — | 550B total / 55B active |
| Context Window | unknown | 524288 | 1M tokens | 1M tokens |
| License / Type | open weights | api only | api only | open weights |
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a 17.8B-parameter Mixture-of-Expe...
nvidia-nemotron-35-lightning-30b-a3b-nvfp4Solar Pro 4
Solar Pro 4 is a large language model from Upstage built for enterprise workflow...
upstage-solar-pro-4Qwen3.8 Max Preview
Preview Qwen flagship for million-token multimodal reasoning and long-horizon ag...
alibaba-qwen3.8-max-previewNemotron 3 Ultra
NVIDIA Nemotron 3 Ultra is a flagship open-weight frontier LLM family engineered...
nvidia-nemotron-3-ultraNVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a 17.8B-parameter Mixture-of-Experts (MoE) text generation model developed by nvidia. Built on the NemotronHForCausalLM architecture using transformers. Supports en, es, fr, de, it, ja language(s). Released on 2026-08-04 with 194 likes and 19,250 downloads on Hugging Face.