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 4 quants, from 132.7 GB (Q3_K_L) to 269.3 GB (Q8_0).
Llama 3 1 Nemotron Ultra 253B v1 is a 253B-parameter Llama model in GGUF format, quantized by lmstudio-community. Its trained context length is 128K tokens. The repository has 4 quant files, from 132.7 GB (Q3_K_L) to 269.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 132.7 GB (4 parts) | 149.1 GB | Too big | Get file → | |
| Q4_K_M | 150.9 GB (4 parts) | 169.5 GB | Too big | Get file → | |
| Q6_K | 207.9 GB (6 parts) | 233.3 GB | Too big | Get file → | |
| Q8_0 | 269.3 GB (7 parts) | 302.1 GB | Too big | Get file → |
What GPU do you need for 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 Llama 3 1 Nemotron Ultra 253B v1 quant should you choose?
Q4_K_M is the usual starting point for 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 Q3_K_L at 132.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama 3 1 Nemotron Ultra 253B v1
How much VRAM does 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 Llama 3 1 Nemotron Ultra 253B v1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 149.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 3 1 Nemotron Ultra 253B v1 GGUF?
It depends on the quant: Q3_K_L is 132.7 GB, Q4_K_M is 150.9 GB, Q6_K is 207.9 GB, Q8_0 is 269.3 GB.
What context length does 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 Llama 3 1 Nemotron Ultra 253B v1 GGUF?
The files are on Hugging Face in the lmstudio-community/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 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.