LL

nvidia Llama 3 1 Nemotron Ultra 253B v1

LlamaGGUF by bartowskiUpdated 2025-05-04
Download on Hugging Face
Parameters253B
Context128K
Layers162
Architecturedeci
Smallest quant53.7 GB
Quick answer

nvidia Llama 3 1 Nemotron Ultra 253B v1 needs about 169.5 GB of memory at Q4_K_M (a 150.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 53.7 GB (IQ1_S) to 269.3 GB (Q8_0).

NVIDIA Llama‑3.1‑Nemotron‑Ultra‑253B‑v1 – 253B parameter reasoning model

NVIDIA Llama‑3.1‑Nemotron‑Ultra‑253B‑v1 is a 253‑billion‑parameter LLM designed for reasoning, chat, and tool‑calling. It supports a 128K token context length and is optimized for inference on a single 8×H100 node. The model is available in multiple GGUF quantizations.

Good at

  • Large‑scale reasoning
  • Instruction following
  • Tool‑calling

Limits

  • No vision support
  • Requires high VRAM for full precision
  • License is NVIDIA Open Model License

Best for

  • AI agent development
  • RAG systems
  • Chatbot back‑ends

Who it’s for. Developers building AI agents, chatbots, or RAG solutions that need high‑accuracy reasoning. The model is suitable for commercial use and can be run with llama.cpp or LM Studio.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S53.7 GB (2 parts) 60.6 GB
Too big Get file →
IQ1_M58.8 GB (2 parts) 66.4 GB
Too big Get file →
IQ2_XXS67.4 GB (2 parts) 76.0 GB
Too big Get file →
IQ2_XS74.9 GB (2 parts) 84.4 GB
Too big Get file →
IQ2_S78.5 GB (2 parts) 88.5 GB
Too big Get file →
IQ2_M85.4 GB (3 parts) 96.2 GB
Too big Get file →
Q2_K93.4 GB (3 parts) 105.1 GB
Too big Get file →
Q2_K_L95.4 GB (3 parts) 107.4 GB
Too big Get file →
IQ3_XXS97.6 GB (3 parts) 109.8 GB
Too big Get file →
IQ3_XS103.3 GB (3 parts) 116.2 GB
Too big Get file →
Q3_K_S109.7 GB (3 parts) 123.4 GB
Too big Get file →
IQ3_M113.5 GB (3 parts) 127.6 GB
Too big Get file →
Q3_K_M121.9 GB (4 parts) 137.0 GB
Too big Get file →
Q3_K_L132.7 GB (4 parts) 149.1 GB
Too big Get file →
Q3_K_XL134.5 GB (4 parts) 151.2 GB
Too big Get file →
IQ4_XS135.4 GB (4 parts) 152.2 GB
Too big Get file →
IQ4_NL143.2 GB (4 parts) 160.9 GB
Too big Get file →
Q4_0143.7 GB (4 parts) 161.5 GB
Too big Get file →
Q4_K_S144.4 GB (4 parts) 162.2 GB
Too big Get file →
Q4_K_M150.9 GB (4 parts) 169.5 GB
Too big Get file →
Q4_K_L152.5 GB (4 parts) 171.3 GB
Too big Get file →
Q4_1158.8 GB (4 parts) 178.4 GB
Too big Get file →
Q5_K_S174.5 GB (5 parts) 195.9 GB
Too big Get file →
Q5_K_M178.5 GB (5 parts) 200.5 GB
Too big Get file →
Q6_K207.9 GB (6 parts) 233.3 GB
Too big Get file →
Q8_0269.3 GB (7 parts) 302.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M. With 16 GB VRAM, IQ2_XXS or IQ2_XS are suitable. For 24 GB VRAM, Q2_K or Q2_K_L provide a good balance of quality and memory. Estimates are approximate.

What GPU do you need for nvidia Llama 3 1 Nemotron Ultra 253B v1?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which nvidia Llama 3 1 Nemotron Ultra 253B v1 quant should you choose?

Q4_K_M is the usual starting point for nvidia Llama 3 1 Nemotron Ultra 253B v1: it balances file size and quality well. Here it is a 150.9 GB file.

The Q8_0 file is 269.3 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 53.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeci
Parameters253B
Layers162
Trained context131,072 tokens

Source

Quantized bybartowski
FamilyLlama
Licenseother
Downloads (HF)1,090
Last updated2025-05-04

Frequently asked questions about nvidia Llama 3 1 Nemotron Ultra 253B v1

How much VRAM does nvidia Llama 3 1 Nemotron Ultra 253B v1 need?

About 169.5 GB at Q4_K_M with an 8K context window. That is the 150.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run nvidia Llama 3 1 Nemotron Ultra 253B v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 60.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of nvidia Llama 3 1 Nemotron Ultra 253B v1 GGUF?

It depends on the quant: IQ1_S is 53.7 GB, IQ1_M is 58.8 GB, IQ2_XXS is 67.4 GB, IQ2_XS is 74.9 GB, IQ2_S is 78.5 GB, IQ2_M is 85.4 GB and 20 more.

What context length does nvidia Llama 3 1 Nemotron Ultra 253B v1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download nvidia Llama 3 1 Nemotron Ultra 253B v1 GGUF?

The files are on Hugging Face in the bartowski/nvidia_Llama-3_1-Nemotron-Ultra-253B-v1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does nvidia Llama 3 1 Nemotron Ultra 253B v1 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the IQ1_S and IQ1_M quantizations fit within 8 GB VRAM, though performance may be limited.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is governed by the NVIDIA Open Model License and the Llama 3.1 Community License Agreement.

Other GGUFs of Llama-3_1-Nemotron-Ultra-253B-v1

Similar models

Browse all →

More from bartowski

All by bartowski →

More Llama models

All Llama →

Other large models

All large models →