Nex-N2.5 — Nex-AGI 的本地 AI 模型

作者: Jakub Rusinowski · 最后更新:

The September 2026 agentic family from Nex-AGI, an innovation alliance initiated by the Shanghai Innovation Institute. Three sizes, all post-trains of other labs' base weights: mini and Pro continue the multimodal Qwen3.5 lineage of Nex-N2, while Max is the alliance's first trillion-scale post-train, built on a 1.6T text-only DeepSeek-V4-Pro base. Vision is treated as an action interface rather than an input mode — the models drive computers and browsers and check their own work from what appears on screen. Max takes BrowseComp at 92.6, ahead of every model in Nex's own comparison table. Only the 35B mini is realistically self-hostable.

变体

Nex-N2.5 最小的变体在 Q4_K_M 下约需 22 GB 显存——量化权重加框架开销,不含 KV 缓存。

模型显存
Nex-N2.5 mini →
35B (3B active)
~21.9 GB
Nex-N2.5 Pro →
397B (17B active)
~240.5 GB
Nex-N2.5 Max →
1.6T (49B active)
~966.8 GB

显存为 Q4_K_M 下的量化权重加开销,与 GPU 与显存检测器使用同一引擎计算。

如何在本地运行 Nex-N2.5

安装 Ollama,然后拉取标签。

ollama run nex-n2-5

在上方选择一个尺寸,查看它自己的显存、速度估算和安装命令。

许可证

Custom Open-Weight允许商业使用

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

适用于: Nex-N2.5 mini, Nex-N2.5 Pro, Nex-N2.5 Max

推荐 GPU

目录中能在本地运行 Nex-N2.5(至少 22 GB 显存)的最便宜 GPU 是 NVIDIA GeForce RTX 5090 (32 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。
NVIDIA GeForce RTX 5090 32GB
32 GB VRAM · 575 W board power
2026年价格波动较大——请以当前商品页价格为准。

我的 GPU 能运行 Nex-N2.5 吗?

Nex-N2.5 — 常见问题

How much VRAM does Nex-N2.5 need?

Nex-N2.5 needs about 22 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Nex-N2.5 mini (22 GB, Q4_K_M); Nex-N2.5 Pro (240 GB, Q4_K_M); Nex-N2.5 Max (967 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run Nex-N2.5 on an RTX 4090 (24 GB)?

Yes — Nex-N2.5 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.

What quantization should I use for Nex-N2.5?

Q4_K_M is the best balance of quality and VRAM for Nex-N2.5 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.

How do I run Nex-N2.5 with Ollama?

Nex-N2.5 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.