Nex-N2.5 — lokalny model AI od Nex-AGI
Autor: Jakub Rusinowski · Ostatnia aktualizacja:
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.
Warianty
Najmniejszy wariant Nex-N2.5 potrzebuje około 22 GB VRAM przy Q4_K_M — skwantyzowane wagi plus narzut frameworka, bez pamięci podręcznej KV.
| Model | VRAM przy Q4 | VRAM | Kontekst | Uruchom |
|---|---|---|---|---|
| Nex-N2.5 mini → 35B (3B active) | ~21.9 GB | 262,144 | ollama run nex-n2-5 | |
| Nex-N2.5 Pro → 397B (17B active) | ~240.5 GB | 262,144 | ollama run nex-n2-5 | |
| Nex-N2.5 Max → 1.6T (49B active) | ~966.8 GB | 262,144 | ollama run nex-n2-5 |
Pamięć to skwantyzowane wagi plus narzut przy Q4_K_M, liczone tym samym silnikiem co sprawdzarka GPU i VRAM.
Jak uruchomić Nex-N2.5 lokalnie
Zainstaluj Ollama, a potem pobierz tag.
ollama run nex-n2-5Wybierz rozmiar powyżej, aby zobaczyć jego VRAM, szacowaną szybkość i polecenie instalacji.
Licencja
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Dotyczy: Nex-N2.5 mini, Nex-N2.5 Pro, Nex-N2.5 MaxPolecane GPU
Najtańsze GPU z naszego katalogu, które uruchomi Nex-N2.5 lokalnie (min. 22 GB VRAM), to NVIDIA GeForce RTX 5090 (32 GB).
Czy uruchomię Nex-N2.5 na moim GPU?
- Nex-N2.5 na AMD Radeon RX 7800 XT
- Nex-N2.5 na AMD Radeon RX 7900 XT
- Nex-N2.5 na AMD Radeon RX 7900 XTX
- Nex-N2.5 na AMD Radeon RX 9060 XT 16GB
- Nex-N2.5 na AMD Radeon RX 9070
- Nex-N2.5 na AMD Radeon RX 9070 XT
- Nex-N2.5 na Apple M1
- Nex-N2.5 na Apple M1 Pro
- Nex-N2.5 na Apple M2
- Nex-N2.5 na Apple M2 Pro
- Nex-N2.5 na Apple M3
- Nex-N2.5 na Apple M3 Pro
- Nex-N2.5 na Apple M3 Ultra
- Nex-N2.5 na Apple M4
- Nex-N2.5 na Apple M4 Pro
- Nex-N2.5 na Apple M5
- Nex-N2.5 na Intel Arc B570
- Nex-N2.5 na Intel Arc B580
- Nex-N2.5 na NVIDIA GeForce RTX 3060 (12GB)
- Nex-N2.5 na NVIDIA GeForce RTX 3080 (10GB)
- Nex-N2.5 na NVIDIA GeForce RTX 3090
- Nex-N2.5 na NVIDIA GeForce RTX 4060 Ti 16GB
- Nex-N2.5 na NVIDIA GeForce RTX 4070
- Nex-N2.5 na NVIDIA GeForce RTX 4070 Super
- Nex-N2.5 na NVIDIA GeForce RTX 4070 Ti
- Nex-N2.5 na NVIDIA GeForce RTX 4070 Ti Super
- Nex-N2.5 na NVIDIA GeForce RTX 4080
- Nex-N2.5 na NVIDIA GeForce RTX 4080 Super
- Nex-N2.5 na NVIDIA GeForce RTX 4090
- Nex-N2.5 na NVIDIA GeForce RTX 5060 Ti 16GB
- Nex-N2.5 na NVIDIA GeForce RTX 5070
- Nex-N2.5 na NVIDIA GeForce RTX 5070 Ti
- Nex-N2.5 na NVIDIA GeForce RTX 5080
- Nex-N2.5 na NVIDIA GeForce RTX 5090
- Nex-N2.5 na NVIDIA L40S
- Nex-N2.5 na NVIDIA RTX 6000 Ada Generation
Nex-N2.5 — najczęściej zadawane pytania
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.