Llama-3_3-Nemotron-Super-49B-V1_5 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 26 quants, from 11.4 GB (IQ1_S) to 99.7 GB (BF16).
Llama‑3.3‑Nemotron‑Super‑49B‑v1.5 – a 49‑billion‑parameter reasoning LLM
Llama‑3.3‑Nemotron‑Super‑49B‑v1.5 is a 49‑billion‑parameter LLM derived from Meta Llama‑3.3‑70B‑Instruct. It supports a 128K‑token context and is post‑trained for reasoning, chat, and tool‑calling tasks. The model is available in multiple GGUF quantizations.
Good at
- Reasoning and instruction following
- Tool calling and RAG support
- Large context handling
Limits
- Requires high VRAM for full precision
- No vision capabilities
- License governed by NVIDIA Open Model License
Best for
- AI agent development
- Chatbot back‑ends
- RAG system integration
Who it’s for. Developers building AI agents, chatbots, or RAG systems that need advanced reasoning and tool‑calling. The model is suitable for commercial use under the NVIDIA Open Model License.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 11.4 GB | 13.3 GB | Too big | Get file → | |
| IQ1_M | 12.4 GB | 14.4 GB | Too big | Get file → | |
| IQ2_XXS | 14.0 GB | 16.1 GB | Too big | Get file → | |
| IQ2_M | 17.3 GB | 19.9 GB | Too big | Get file → | |
| Q2_K | 18.7 GB | 21.5 GB | Too big | Get file → | |
| Q2_K_L | 19.0 GB | 21.8 GB | Too big | Get file → | |
| Q2_K_XL | 19.3 GB | 22.1 GB | Too big | Get file → | |
| IQ3_XXS | 19.7 GB | 22.6 GB | Too big | Get file → | |
| Q3_K_S | 22.0 GB | 25.1 GB | Too big | Get file → | |
| Q3_K_M | 24.3 GB | 27.7 GB | Too big | Get file → | |
| Q3_K_XL | 24.8 GB | 28.3 GB | Too big | Get file → | |
| IQ4_XS | 26.9 GB | 30.6 GB | Too big | Get file → | |
| IQ4_NL | 28.4 GB | 32.3 GB | Too big | Get file → | |
| Q4_0 | 28.5 GB | 32.4 GB | Too big | Get file → | |
| Q4_K_S | 28.6 GB | 32.6 GB | Too big | Get file → | |
| Q4_K_M | 30.2 GB | 34.3 GB | Too big | Get file → | |
| Q4_K_XL | 30.4 GB | 34.5 GB | Too big | Get file → | |
| Q4_1 | 31.4 GB | 35.6 GB | Too big | Get file → | |
| Q5_K_S | 34.4 GB | 39.1 GB | Too big | Get file → | |
| Q5_K_M | 35.4 GB | 40.1 GB | Too big | Get file → | |
| Q5_K_XL | 35.4 GB | 40.2 GB | Too big | Get file → | |
| Q6_K | 40.9 GB | 46.3 GB | Too big | Get file → | |
| Q6_K_XL | 43.4 GB | 49.1 GB | Too big | Get file → | |
| Q8_0 | 53.0 GB (2 parts) | 59.9 GB | Too big | Get file → | |
| Q8_K_XL | 58.7 GB (2 parts) | 66.2 GB | Too big | Get file → | |
| BF16 | 99.7 GB (2 parts) | 112.2 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (11.45 GB, ~13.3 GB memory at 8K context). For 12‑GB VRAM, IQ1_M (12.37 GB, ~14.4 GB). For 24‑GB VRAM, Q4_K_M (30.22 GB, ~34.3 GB). Larger VRAM allows higher‑quality quants such as Q5_K_XL or Q6_K_XL.
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: 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_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 30.2 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 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
Source
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 34.3 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_5 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_5 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 20 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 unsloth/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?
Use the IQ1_S quant, which is 11.45 GB and requires about 13.3 GB of VRAM at 8K context.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The NVIDIA Open Model License governs use of this model.