Nex-AGI397B (17B active)~240 GB VRAM at Q4_K_M

Nex-N2.5 Pro — VRAM, speed & local setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Written by Jakub Rusinowski · Last updated September 8, 2026

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.

Logic92

Creative87

Coding93

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.

Quant	VRAM	Speed (est.)	Fit
Q2_K 2.63 bpw	131.3 GB	—	Too big
Q3_K_M 3.41 bpw	170 GB	—	Too big
Q4_K_M 4.83 bpw	240.5 GB	—	Too big
Q5_K_M 5.67 bpw	282.2 GB	—	Too big
Q6_K 6.56 bpw	326.3 GB	—	Too big
Q8_0 8.50 bpw	422.6 GB	—	Too big
F16 16.00 bpw	794.8 GB	—	Too big

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Nex-N2.5 Pro VRAM calculator →

Get Nex-N2.5 Pro running

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

Buy this hardware Apple Mac Studio M3 Ultra — 512 GB VRAM · 60 W board power Deploy in the cloud now RunPod

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.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.

Apple Mac Studio M3 Ultra

512 GB VRAM · 60 W board power

2026 prices are volatile — check the current listing.

Check price on Amazon

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 ↗

Specifications

Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.

Parameters: 397 Billion (17B active)
Context window: 262,144
Architecture: Mixture-of-Experts (Qwen3.5-397B-A17B base, multimodal)
Provider: Nex-AGI
Licence: Open-weight (terms unpublished)
Practical deployment: Workstation (large unified memory or pro GPU)
Specified at: Q4_K_M
System RAM: 256 GB
Record updated: 2026-09-08

LicenceCustom Open-WeightCommercial use permitted

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

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best foragentic taskssoftware engineeringenterprisemultimodal

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.