nvidia / text-generation updated 1 month ago

NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

Name: NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
Author: nvidia

:---:--- Total Parameters 550B (55B active) Architecture LatentMoE - Mamba-2 + MoE + Attention hybrid with Multi-Token Prediction (MTP) Context Length Up to 1M tokens Minimum GPU Requirement 4xGB200, 4xB200, 4x GB300, 4x B300, 8xH100 Supported Languages English, French, Spanish, Italian, German, Japanese, Hindi, Korean, Brazilian Portuguese, and Chinese Best For Frontier reasoning, complex agentic workflows, long-con...

Params

335.0 B

Context

262,144

Downloads 30d

233 K

Likes

279

Licence: other Not gated SAFETENSORS 12 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

257 K233 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	u8	352.3 GB	438.3 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 256K ctx	352.3 GB	1,996.2 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/nvidia-nemotron-3-ultra-550b-a55b-nvfp4
{
  "hf_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4",
  "params_b": 335.04,
  "context_length": 262144,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 233194,
  "vram_estimates": [
    { "quant": "u8", "gb": 438.3 }
  ],
  "updated_at": "2026-07-28T18:07:11Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: NemotronHForCausalLM
Parameters: 335.0 B
Tensor type: U8
Context length: 262,144
Vocabulary: 131,072
Licence: other
First seen on the Hub: 2026-06-03
Training datasets: nvidia/nemotron-post-training-v3, nvidia/nemotron-pre-training-datasets
Added to our catalog: 2026-07-28

Compare with

DeepSeek-R1 9.9 M gpt-oss-120b 4.2 M DeepSeek-V4-Flash 2.7 M GLM-5.2-FP8 2.7 M GLM-5.2 2.2 M GLM-5.2-NVFP4 1.8 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB