LL

Nemotron Super 49B v1.5 Uncensored

LlamaGGUF by timteh673Updated 2026-03-31
Download on Hugging Face
Parameters49.9B
Context128K
Layers80
Architecturedeci
Smallest quant18.7 GB
Quick answer

Nemotron Super 49B v1.5 Uncensored 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 7 quants, from 18.7 GB (Q2_K) to 99.7 GB (BF16).

Nemotron Super 49B v1.5 Uncensored – a 49.9B parameter LLM with 128K context

Nemotron Super 49B v1.5 Uncensored is a 49.9B parameter model based on Llama‑3.3‑Nemotron‑Super‑49B‑v1.5. It supports a context length of 131072 tokens and is post‑trained for reasoning, tool calling, and agentic tasks. The model is released under the llama3.3 license.

Good at

  • Reasoning
  • Tool calling
  • Agentic tasks

Limits

  • No vision support
  • Requires large VRAM
  • License restricts commercial use

Best for

  • Chatbots needing deep reasoning
  • Tool‑enabled agents
  • RAG workflows

Who it’s for. Developers building advanced conversational agents that require high‑level reasoning and tool integration. The model is suitable for research and production environments with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K18.7 GB 21.5 GB
Too big Get file →
Q3_K_M24.3 GB 27.7 GB
Too big Get file →
Q4_K_M30.2 GB 34.3 GB
Too big Get file →
Q5_K_M35.4 GB 40.1 GB
Too big Get file →
Q6_K40.9 GB 46.3 GB
Too big Get file →
Q8_053.0 GB 59.9 GB
Too big Get file →
BF1699.7 GB 112.2 GB
Too big Get file →

For a 8 GB VRAM GPU the smallest quant available is Q2_K, which estimates 21.5 GB memory at 8 k context – still above 8 GB. A more realistic choice is Q4_K_M, estimating 34.3 GB. If you have a 16 GB or 24 GB GPU, Q4_K_M or Q5_K_M (40.1 GB) may be viable. Memory estimates are approximate.

What GPU do you need for Nemotron Super 49B v1.5 Uncensored?

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: the best quant that fits is Q2_K (18.7 GB file, about 21.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_M (24.3 GB file, about 27.7 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 Nemotron Super 49B v1.5 Uncensored quant should you choose?

Q4_K_M is the usual starting point for Nemotron Super 49B v1.5 Uncensored: it balances file size and quality well. Here it is a 30.2 GB file.

The Q8_0 file is 53.0 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 Q2_K at 18.7 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
Parameters49.9B
Layers80
Trained context131,072 tokens

Source

Quantized bytimteh673
FamilyLlama
Licensellama3.3
Downloads (HF)628
Last updated2026-03-31

Frequently asked questions about Nemotron Super 49B v1.5 Uncensored

How much VRAM does Nemotron Super 49B v1.5 Uncensored 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 Nemotron Super 49B v1.5 Uncensored on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nemotron Super 49B v1.5 Uncensored GGUF?

It depends on the quant: Q2_K is 18.7 GB, Q3_K_M is 24.3 GB, Q4_K_M is 30.2 GB, Q5_K_M is 35.4 GB, Q6_K is 40.9 GB, Q8_0 is 53.0 GB and 1 more.

What context length does Nemotron Super 49B v1.5 Uncensored support?

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

Where can I download Nemotron Super 49B v1.5 Uncensored GGUF?

The files are on Hugging Face in the timteh673/Nemotron-Super-49B-v1.5-Uncensored-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 Nemotron Super 49B v1.5 Uncensored use?

Hugging Face lists the license as llama3.3. 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 Nemotron Super 49B v1.5 on a single 8 GB GPU?

No. The smallest quant requires about 21.5 GB VRAM at 8 k context, exceeding 8 GB.

What quant is best for a 16 GB GPU?

Q4_K_M estimates 34.3 GB, which is still above 16 GB; a 24 GB GPU would handle Q4_K_M or Q5_K_M.

Does the model support image inputs?

No, the model has no vision capabilities.

Other GGUFs of Llama-3_3-Nemotron-Super-49B-v1_5

Similar models

Browse all →

More from timteh673

All by timteh673 →

More Llama models

All Llama →

Other large models

All large models →