LL

Llama-3_3-Nemotron-Super-49B-V1

LlamaGGUF by unslothUpdated 2025-05-22
Download on Hugging Face
Parameters49.9B
Context128K
Layers80
Architecturedeci
Smallest quant11.4 GB
Quick answer

Llama-3_3-Nemotron-Super-49B-V1 needs about 34.3 GB of memory at Q4_K_M (a 30.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 24 quants, from 11.4 GB (IQ1_S) to 99.7 GB (BF16).

Llama‑3.3‑Nemotron‑Super‑49B‑v1 – a 49.9B reasoning‑focused LLM

Llama‑3.3‑Nemotron‑Super‑49B‑v1 is a 49.9B‑parameter model built on Meta Llama‑3.3‑70B‑Instruct. It supports a context length of 128K tokens and is post‑trained for reasoning, chat, RAG, and tool calling. The model is ready for commercial use under the NVIDIA Open Model License.

Good at

  • Reasoning tasks
  • Chat and instruction following
  • Tool calling

Limits

  • Large context length requires high VRAM
  • No vision support
  • License is NVIDIA Open Model License

Best for

  • Developing AI agents
  • Building RAG systems
  • Instruction‑following chatbots

Who it’s for. Developers and researchers building AI agents, chatbots, or RAG systems that need strong reasoning capabilities. The model is suitable for commercial deployment under the NVIDIA Open Model License.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S11.4 GB 13.3 GB
Too big Get file →
IQ1_M12.4 GB 14.4 GB
Too big Get file →
IQ2_XXS14.0 GB 16.1 GB
Too big Get file →
IQ2_M17.3 GB 19.9 GB
Too big Get file →
Q2_K18.7 GB 21.5 GB
Too big Get file →
Q2_K_L19.0 GB 21.8 GB
Too big Get file →
Q2_K_XL19.3 GB 22.1 GB
Too big Get file →
IQ3_XXS19.7 GB 22.6 GB
Too big Get file →
Q3_K_S22.0 GB 25.1 GB
Too big Get file →
Q3_K_M24.3 GB 27.7 GB
Too big Get file →
Q3_K_XL24.8 GB 28.3 GB
Too big Get file →
IQ4_XS26.9 GB 30.6 GB
Too big Get file →
IQ4_NL28.4 GB 32.3 GB
Too big Get file →
Q4_K_S28.6 GB 32.6 GB
Too big Get file →
Q4_K_M30.2 GB 34.3 GB
Too big Get file →
Q4_K_XL30.4 GB 34.5 GB
Too big Get file →
Q4_131.4 GB 35.6 GB
Too big Get file →
Q5_K_S34.4 GB 39.1 GB
Too big Get file →
Q5_K_M35.4 GB 40.1 GB
Too big Get file →
Q5_K_XL35.4 GB 40.2 GB
Too big Get file →
Q6_K40.9 GB 46.3 GB
Too big Get file →
Q6_K_XL43.4 GB 49.1 GB
Too big Get file →
Q8_K_XL58.7 GB (2 parts) 66.2 GB
Too big Get file →
BF1699.7 GB (2 parts) 112.2 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (11.45 GB file, 13.3 GB memory at 8K context). For 16‑GB VRAM, IQ2_XXS (13.95 GB file, 16.1 GB memory) or Q2_K (18.74 GB file, 21.5 GB memory). For 32‑GB VRAM, Q4_K_M (30.22 GB file, 34.3 GB memory) or Q5_K_S (34.43 GB file, 39.1 GB memory).

What GPU do you need for Llama-3_3-Nemotron-Super-49B-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: the best quant that fits is IQ1_M (12.4 GB file, about 14.4 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_XXS (19.7 GB file, about 22.6 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ4_XS (26.9 GB file, about 30.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (40.9 GB file, about 46.3 GB in use).

Which Llama-3_3-Nemotron-Super-49B-V1 quant should you choose?

Q4_K_M is the usual starting point for Llama-3_3-Nemotron-Super-49B-V1: it balances file size and quality well. Here it is a 30.2 GB file.

If memory is tight, the smallest file is IQ1_S at 11.4 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
Parameters49.9B
Layers80
Trained context131,072 tokens

Source

Quantized byunsloth
FamilyLlama
Licenseother
Downloads (HF)2,268
Last updated2025-05-22

Frequently asked questions about Llama-3_3-Nemotron-Super-49B-V1

How much VRAM does Llama-3_3-Nemotron-Super-49B-V1 need?

About 34.3 GB at Q4_K_M with an 8K context window. That is the 30.2 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 Llama-3_3-Nemotron-Super-49B-V1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama-3_3-Nemotron-Super-49B-V1 GGUF?

It depends on the quant: IQ1_S is 11.4 GB, IQ1_M is 12.4 GB, IQ2_XXS is 14.0 GB, IQ2_M is 17.3 GB, Q2_K is 18.7 GB, Q2_K_L is 19.0 GB and 18 more.

What context length does Llama-3_3-Nemotron-Super-49B-V1 support?

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

Where can I download Llama-3_3-Nemotron-Super-49B-V1 GGUF?

The files are on Hugging Face in the unsloth/Llama-3_3-Nemotron-Super-49B-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 Llama-3_3-Nemotron-Super-49B-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 quant requires 13.3 GB memory at 8K context, which fits on 8 GB VRAM with some overhead.

Does this model support vision?

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 3.3 Community License Agreement.

Other GGUFs of Llama-3_3-Nemotron-Super-49B-v1

Similar models

Browse all →

More from unsloth

All by unsloth →

More Llama models

All Llama →

Other large models

All large models →