Nex-N2.5-Pro: hardware requirements
Nex-N2.5-Pro needs about 255 GB of memory at Q4_K_M quantization: a 251 GB download plus room for context and a runtime allowance. That is beyond consumer hardware; use it through an API instead.
This is a mixture-of-experts model. Only a fraction of its 397B parameters are used for each token, so it runs faster than its size suggests, but all of it still has to fit in memory. The speed is that of a small model; the memory requirement is that of a large one. More on this →
Will it run on your machine?
Use it without your own hardware
OpenRouter lists Nex-N2.5-Pro at $0.075 per million input tokens and $0.25 per million output tokens.
Price as listed on OpenRouter today. Speed is for hosted servers, not a home computer.
Download sizes by quantization
Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?
| Quant | Download | RAM @ 4K | RAM @ 32K | Source |
|---|---|---|---|---|
| Q4_K_Mrecommended | 251 GB | 255 GB | 258 GB | bartowski/Nex-N2.5-Pro-GGUF |
| Q5_K_M | 306 GB | 309 GB | 313 GB | bartowski/Nex-N2.5-Pro-GGUF |
| Q6_K | 350 GB | 354 GB | 357 GB | bartowski/Nex-N2.5-Pro-GGUF |
| Q8_0 | 422 GB | 425 GB | 429 GB | bartowski/Nex-N2.5-Pro-GGUF |
Download sizes are measured from the published files named in the Source column. The RAM columns add the context cache, calculated from the model's configuration, and a runtime allowance of 10% of the download (at least 0.5GB, at most 3GB).