// NVIDIA Nemotron · Text LLM
Nemotron-3-Labs-Ultra-Math-RL: VRAM & local deployment
550B total · 55B active (MoE) parameters. About 367 GB at 4-bit and 1.21 TB at BF16 with one 8K-token request.
released 2026-09-02licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | NVIDIA · nvidia |
|---|---|
| Family / series | NVIDIA Nemotron · Nemotron-3-Labs-Ultra-Math-RL |
| Type | Text LLM (text-generation) |
| Parameters | 550B total · 55B active (MoE) Source: official model card“Number of model parameters: 550B Total / 55B Active” |
| Context length | 256K tokens (262,144)max_position_embeddings in config.json |
| Architecture | 108 layers (12 full-attention) · GQA+HYBRID · MoE |
| Released weights | BF16 · 1.12 TBdownload |
| Licence | OpenMDW-1.1 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2026-09-02 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Total @ 128K | Smallest GPU | Mac |
|---|---|---|---|---|---|---|
| BF16 / FP16 (original) | 1.10 TB | 1.21 TB | 1.21 TB | 1.21 TB | 8 × B200 (1,440GB) | — |
| FP8 / INT8 / Q8_0 | 584 GB | 643 GB | 644 GB | 645 GB | 8 × H200 (1,128GB) | — |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 333 GB | 367 GB | 368 GB | 369 GB | 8 × H100 (640GB) | — |
KV cache per request: 8K 0.1 GB · 32K 0.4 GB · 128K 1.6 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- Transformers — mentioned in the official model card
04Official repositories & quantised builds
1 official repo(s) from nvidia.
05Other NVIDIA Nemotron models
All 62 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 | 3.98B | 3.6 GB | 2026-10-16 |
| Nemotron-3.5-Rerank-8B-BF16 | 8.38B | 6.1 GB | 2026-10-15 |
| NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 | 124.5B / 12B | 83.5 GB | 2026-10-12 |
| NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16 | 74.9B / 9B | 50.4 GB | 2026-10-09 |
| Nemotron-3.5-Embed-1B-BF16 | 1.55B | 1.5 GB | 2026-10-07 |
| Nemotron-3.5-Embed-8B-BF16 | 8.38B | 6.1 GB | 2026-10-07 |
| Nemotron-3.5-Parse | 631M | 1.1 GB | 2026-09-03 |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 31.6B / 3B | 21.6 GB | 2026-08-01 |
06Sources
Data checked 2026-09-11. Parameters, context and licence are copied from the official repository; memory figures are our estimates.