Skip to content
Regolo Logo
Regolo Logo

Nex-N2-mini

Nex‑N2‑mini is a 35B (3B active) agentic MoE model built on Qwen3.5‑35B‑A3B‑Base, tuned for coding and tool‑using agents with a 262k context window and stronger GDPVal/agent scores than the stock 35B base model.
Custom Model
Chat

Getting Started

Step 1

Sign Up and get your Api Key and use with UNLIMITED tokens for 30 days.

Step 2

Paste the URL from Huggingface repository: https://huggingface.co/nex-agi/Nex-N2-mini

Step 3

Choose the GPU machine to deploy.

That’s all! You’re ready to use the model in few minutes without infrastructure complexity in few minutes.

Additional Information

Applications & Use Cases

  • Coding‑centric agents that read and modify medium‑sized repositories, using Qwen3.5‑35B’s MoE backbone plus Nex’s agent tuning for tool calls and iterative fixes.
  • Long‑context assistants that work over specs, tickets, and code up to 262k tokens, where you want an agent‑optimized model smaller than Nex‑N2‑Pro.
  • Local or workstation deployments that target a 35B MoE model with 3B active parameters for better latency and VRAM use compared with 400B‑class models.
  • Benchmarking and experimentation with Nex’s Agentic Thought framework before moving heavy workloads to Nex‑N2‑Pro.