NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
--- 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
1.1 M
Likes
384
Download history
daily snapshots · 106 days
▲ 261 K in the last 30 days (32.4%)
1.5 M829 K
Oct 12Oct 22Nov 1Nov 10
1.5 M213 K
Aug 13Sep 12Oct 12Nov 10
1.5 M213 K
Jul 28Sep 1Oct 6Nov 10
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 -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": 1067799,
"vram_estimates": [
{ "quant": "bf16", "gb": 1317.7 }
],
"updated_at": "2026-08-25T01:00:39Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-11-10$0.60
input / 1M
$2.40
output / 1M
$0.12
cached input / 1M
$3.00
1M in + 1M out
:free variant
Free in · Free out
- Context window
- 202,800 tokens
- Max output
- 182,520 tokens
- Providers
- 3
- Cheapest provider
- DeepInfra · $0.40 / $1.76
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 11.8 / 49.3 / 20.1
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
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 any text-generation model