Nex-N2.5-Pro needs about 265.9 GB of memory at Q4_K_M (a 264.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 188.6 GB (IQ3_S) to 309.8 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.0 GB.
Nex-N2.5-Pro is a 396B-parameter Nex model in GGUF format, quantized by vultr. Its trained context length is 256K tokens. The repository has 4 quant files, from 188.6 GB (IQ3_S) to 309.8 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 188.6 GB (2 parts) | 190.1 GB | Too big | Get file → | |
| IQ3_M | 190.8 GB (2 parts) | 192.3 GB | Too big | Get file → | |
| Q4_K_M | 264.4 GB (2 parts) | 265.9 GB | Too big | Get file → | |
| Q5_K_M | 309.8 GB (3 parts) | 311.3 GB | Too big | Get file → |
What GPU do you need for Nex-N2.5-Pro?
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 Nex-N2.5-Pro quant should you choose?
Q4_K_M is the usual starting point for Nex-N2.5-Pro: it balances file size and quality well. Here it is a 264.4 GB file.
If memory is tight, the smallest file is IQ3_S at 188.6 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 Nex-N2.5-Pro
How much VRAM does Nex-N2.5-Pro need?
About 265.9 GB at Q4_K_M with an 8K context window. That is the 264.4 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 Nex-N2.5-Pro on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 190.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nex-N2.5-Pro GGUF?
It depends on the quant: IQ3_S is 188.6 GB, IQ3_M is 190.8 GB, Q4_K_M is 264.4 GB, Q5_K_M is 309.8 GB.
What context length does Nex-N2.5-Pro support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.0 GB at 8K and 4.0 GB at 32K.
Where can I download Nex-N2.5-Pro GGUF?
The files are on Hugging Face in the vultr/Nex-N2.5-Pro-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 Nex-N2.5-Pro use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.