NVIDIA Nemotron Labs 3 Puzzle 75B A9B MTP needs about 71.3 GB of memory at Q5_K_M (a 58.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 45.3 GB (IQ4_NL) to 156.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 48.3 GB.
NVIDIA Nemotron Labs 3 Puzzle 75B A9B MTP is a 78.3B-parameter Nemotron model in GGUF format, quantized by MRockatansky. Its trained context length is 1024K tokens. The repository has 4 quant files, from 45.3 GB (IQ4_NL) to 156.8 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_NL | 45.3 GB | 57.9 GB | Too big | Get file → | |
| Q5_K_M | 58.7 GB | 71.3 GB | Too big | Get file → | |
| Q6_K | 67.2 GB | 79.8 GB | Too big | Get file → | |
| BF16 | 156.8 GB | 169.4 GB | Too big | Get file → |
What GPU do you need for NVIDIA Nemotron Labs 3 Puzzle 75B A9B MTP?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 NVIDIA Nemotron Labs 3 Puzzle 75B A9B MTP quant should you choose?
Q5_K_M (58.7 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is IQ4_NL at 45.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about NVIDIA Nemotron Labs 3 Puzzle 75B A9B MTP
How much VRAM does NVIDIA Nemotron Labs 3 Puzzle 75B A9B MTP need?
About 71.3 GB at Q5_K_M with an 8K context window. That is the 58.7 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 NVIDIA Nemotron Labs 3 Puzzle 75B A9B MTP on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 57.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NVIDIA Nemotron Labs 3 Puzzle 75B A9B MTP GGUF?
It depends on the quant: IQ4_NL is 45.3 GB, Q5_K_M is 58.7 GB, Q6_K is 67.2 GB, BF16 is 156.8 GB.
What context length does NVIDIA Nemotron Labs 3 Puzzle 75B A9B MTP support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 12.1 GB at 8K and 48.3 GB at 32K.
Where can I download NVIDIA Nemotron Labs 3 Puzzle 75B A9B MTP GGUF?
The files are on Hugging Face in the MRockatansky/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-MTP-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 NVIDIA Nemotron Labs 3 Puzzle 75B A9B MTP 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.