Nex-N2.5 Pro — VRAM, Speed & Local Setup

作者： Jakub Rusinowski · 最后更新： 2026年9月8日

Model library → Nex-N2.5 → Nex-N2.5 Pro

Nex's mid-tier at 240 GB in Q4_K_M — a rack, not a desk, and Nex serves it on 8x H100. Reads 17B parameters per token. Scores 82.7 on Terminal-Bench 2.1 and 82.2 on OSWorld-Verified, roughly matching Claude Opus 5 on computer-use while trailing it on SWE-Bench Pro (61.2 vs 79.2). Counts are inherited from the Qwen3.5-397B-A17B base Nex-N2 names, not published for N2.5 directly.

Nex-N2.5 Pro needs about 240 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters397 Billion (17B active)
Context window262,144
ArchitectureMixture-of-Experts (Qwen3.5-397B-A17B base, multimodal)
ProviderNex-AGI
LicenceOpen-weight (terms unpublished)
Specified atQ4_K_M
System RAM256 GB
Record updated2026-09-08

Licence

Custom Open-Weight — commercial use permitted. Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K130.5 GB131.3 GB—Won't fit
Q3_K_M169.2 GB170.0 GB—Won't fit
Q4_K_M239.7 GB240.5 GB—Won't fit
Q5_K_M281.4 GB282.2 GB—Won't fit
Q6_K325.5 GB326.3 GB—Won't fit
Q8_0421.8 GB422.6 GB—Won't fit
F16794.0 GB794.8 GB—Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the Nex-N2.5 Pro VRAM calculator.

Buy This HardwareApple Mac Studio M3 Ultra — 512 GB VRAM · 60 W board powerDeploy in the Cloud NowRunPod

or compare on Vast.ai

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs Nex-N2.5 Pro is the Apple M3 Ultra (512 GB).

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。
Apple Mac Studio M3 Ultra
512 GB VRAM · 60 W board power
2026年价格波动较大——请以当前商品页价格为准。
在亚马逊查看价格

How to Run Nex-N2.5 Pro

Install Ollama, then run:

ollama run nex-n2-5

Weights on Hugging Face: nex-agi/Nex-N2.5-Pro.

Best for: agentic tasks, software engineering, enterprise, multimodal.

Can I Run Nex-N2.5 Pro on My GPU?

Other Nex-N2.5 Sizes

Nex-N2.5 Pro — Frequently Asked Questions

How much VRAM does Nex-N2.5 Pro need?
About 240 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Nex-N2.5 Pro run on an RTX 4090 (24 GB)?
No. Nex-N2.5 Pro needs about 240 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run Nex-N2.5 Pro locally?
Install Ollama and run `ollama run nex-n2-5`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Nex-N2.5 come in?
Nex-N2.5 mini (22 GB), Nex-N2.5 Pro (240 GB), Nex-N2.5 Max (967 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All Nex-N2.5 models | VRAM calculator | Check your own hardware