nvidia / text-generation updated 1 month ago

NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

Name: NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Author: nvidia

--- libraryname: transformers license: other licensename: openmdw-1.1 licenselink: >- https://openmdw.ai/license/1-1/ pipelinetag: text-generation language: - en - fr - es - it - de - pt - ja - ko - hi - ar - zh - he tags: - nvidia - pytorch - nemotron-3 - latent-moe - mtp datasets: - nvidia/nemotron-post-training-v3 - nvidia/nemotron-pre-training-datasets trackdownloads: true ---

Params

560.5 B

Context

262,144

Downloads 30d

469 K

Likes

304

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

Download history

daily snapshots · 10 days

469 K339 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	bf16	1,121.1 GB	1,317.7 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 256K ctx	1,121.1 GB	3,924.2 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-bf16
{
  "hf_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16",
  "params_b": 560.52,
  "context_length": 262144,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 468923,
  "vram_estimates": [
    { "quant": "bf16", "gb": 1317.7 }
  ],
  "updated_at": "2026-07-28T18:06:15Z"
}

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

Specifications

Architecture: NemotronHForCausalLM
Parameters: 560.5 B
Tensor type: BF16
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 GLM-5.2-FP8 2.7 M GLM-5.2 2.2 M GLM-5.2-NVFP4 1.8 M DeepSeek-V3.2 1.2 M DeepSeek-V3 1.2 M

Appears in

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