LL

Llama-3_3-Nemotron-Super-49B-v1_5

LlamaGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters49.9B
Context128K
Layers80
Architecturedeci
Smallest quant0.0 GB
Quick answer

Llama-3_3-Nemotron-Super-49B-v1_5 needs about 34.8 GB of memory at Q4_K_M (a 30.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 32 quants, from 0.0 GB to 99.7 GB (F16).

49.9B‑parameter Llama‑3.3‑Nemotron‑Super‑49B‑v1.5

Llama‑3.3‑Nemotron‑Super‑49B‑v1.5 is a 49.9B‑parameter reasoning model with a 128K token context length. It is post‑trained for reasoning, human chat preferences, and tool‑calling tasks. The model is available in multiple GGUF quantizations.

Good at

  • Reasoning
  • Tool calling
  • Large context

Limits

  • No vision support
  • Requires large VRAM for higher‑bit quantizations
  • License is other

Best for

  • Chatbots needing long context
  • RAG pipelines
  • Agentic task automation

Who it’s for. Developers building chat or agent systems that require deep reasoning and long‑context handling. The model is suitable for users with access to high‑memory GPUs or CPU setups that can handle large quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
IQ1_S13.7 GB 15.8 GB
Too big Get file →
IQ1_M14.9 GB 17.2 GB
Too big Get file →
IQ2_XXS15.3 GB 17.7 GB
Too big Get file →
IQ2_XS16.8 GB 19.3 GB
Too big Get file →
IQ2_S17.4 GB 20.0 GB
Too big Get file →
IQ2_M18.3 GB 21.1 GB
Too big Get file →
Q2_K_S19.0 GB 21.8 GB
Too big Get file →
Q2_K_M19.3 GB 22.1 GB
Too big Get file →
IQ3_XXS20.8 GB 23.8 GB
Too big Get file →
IQ3_XS21.4 GB 24.5 GB
Too big Get file →
IQ3_S23.7 GB 27.0 GB
Too big Get file →
IQ3_M24.0 GB 27.4 GB
Too big Get file →
Q3_K_S24.2 GB 27.6 GB
Too big Get file →
Q3_K_M24.7 GB 28.2 GB
Too big Get file →
IQ4_XS26.9 GB 30.6 GB
Too big Get file →
Q4_028.1 GB 31.9 GB
Too big Get file →
IQ4_NL28.4 GB 32.3 GB
Too big Get file →
Q4_K_S29.3 GB 33.3 GB
Too big Get file →
Q4_K_M30.6 GB 34.8 GB
Too big Get file →
Q4_131.2 GB 35.4 GB
Too big Get file →
Q5_034.3 GB 38.9 GB
Too big Get file →
Q5_K_S35.2 GB 39.9 GB
Too big Get file →
Q5_K_M35.7 GB 40.4 GB
Too big Get file →
Q5_137.4 GB 42.4 GB
Too big Get file →
Q6_K_M40.9 GB 46.3 GB
Too big Get file →
Q8_053.0 GB 59.9 GB
Too big Get file →
BF1663.6 GB (2 parts) 71.8 GB
Too big Get file →
BF1671.0 GB (2 parts) 80.1 GB
Too big Get file →
F1671.0 GB (2 parts) 80.1 GB
Too big Get file →
BF1699.7 GB (3 parts) 112.2 GB
Too big Get file →
F1699.7 GB (3 parts) 112.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (13.66 GB file, 15.8 GB memory at 8K context). For 16 GB VRAM, IQ2_M (18.35 GB file, 21.1 GB memory) or Q2_K_M (19.26 GB file, 22.1 GB memory). For 32 GB VRAM, Q4_K_M (30.6 GB file, 34.8 GB memory) or Q5_K_M (35.66 GB file, 40.4 GB memory).

What GPU do you need for Llama-3_3-Nemotron-Super-49B-v1_5?

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: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ1_S (13.7 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_XXS (20.8 GB file, about 23.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_0 (28.1 GB file, about 31.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K_M (40.9 GB file, about 46.3 GB in use).

Which Llama-3_3-Nemotron-Super-49B-v1_5 quant should you choose?

Q4_K_M is the usual starting point for Llama-3_3-Nemotron-Super-49B-v1_5: it balances file size and quality well. Here it is a 30.6 GB file.

The Q8_0 file is 53.0 GB, about 1.7 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeci
Parameters49.9B
Layers80
Trained context131,072 tokens

Source

Quantized byMungert
FamilyLlama
Licenseother
Downloads (HF)884
Last updated2025-09-24

Frequently asked questions about Llama-3_3-Nemotron-Super-49B-v1_5

How much VRAM does Llama-3_3-Nemotron-Super-49B-v1_5 need?

About 34.8 GB at Q4_K_M with an 8K context window. That is the 30.6 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_5 on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama-3_3-Nemotron-Super-49B-v1_5 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 13.7 GB, IQ1_M is 14.9 GB, IQ2_XXS is 15.3 GB, IQ2_XS is 16.8 GB, IQ2_S is 17.4 GB and 26 more.

What context length does Llama-3_3-Nemotron-Super-49B-v1_5 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_5 GGUF?

The files are on Hugging Face in the Mungert/Llama-3_3-Nemotron-Super-49B-v1_5-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_5 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 Llama‑3.3‑Nemotron‑Super‑49B‑v1.5 on 8 GB VRAM?

Only the lowest‑bit quantizations such as IQ1_S or IQ1_M are feasible on 8 GB VRAM. Higher‑bit quantizations will exceed the memory limit.

Does the model support vision?

No, the model does not include vision capabilities.

What context length does the model support?

The model supports a context length of 128K tokens.

Similar models

Browse all →

More from Mungert

All by Mungert →

More Llama models

All Llama →

Other large models

All large models →