Overview
Nex-N2-mini is a 35.1B-parameter open-weight model from nex-agi, built on the Qwen3.5-35B-A3B-Base. It uses a Mixture-of-Experts (MoE) design: the full model holds 35B parameters, but only about 3B activate per token, so it runs far lighter than its total size suggests. nex-agi tuned it as an agent model for coding, tool calling, and long-horizon tasks, with an "Agentic Thinking" approach that decides when to reason and how deeply.
The local-AI angle is the point of listing it on Atomic Chat. You download the weights once and run the model on your own machine, so prompts and code never leave your hardware. It works fully offline after the download, which keeps private repos, documents, and chats on-device.
What it is good at
Nex-N2-mini carries the tools, thinking, vision, reasoning, and code capabilities of the Nex-N2 line. Its strongest results are in agentic coding and tool use.
- Agentic coding — it scores 74.4 on SWE-Bench Verified and 60.7 on Terminal-Bench 2.1, so it can read a repo, edit files, and run terminal commands across multi-step tasks.
- Tool calling and reasoning — function calling plus explicit reasoning traces let it plan, call a tool, read the result, and adjust. It reaches 82.6 on GPQA Diamond for hard reasoning questions.
- Vision and long context — the model accepts image-text-to-text input and handles a 256K-token context, useful for screenshots, diagrams, and large codebases or documents in one session.
Running it locally
The model is 35.1B parameters total with a 256K context window, but the 3B active-parameter MoE keeps memory modest. At a Q4 quantization the weights sit around 21 GB, which fits a 24 GB GPU like an RTX 3090, 4090, or 5090, or a Mac with 32 GB or more of unified memory. With CPU offloading through llama.cpp it has been run on far smaller cards at lower speeds.
huggingface-cli download nex-agi/Nex-N2-mini
You can serve the full-precision weights with Transformers or vLLM, or use a GGUF quant in a llama.cpp-based runtime. In Atomic Chat the model loads with one click, with no server setup or command line needed.
License
Nex-N2-mini is released under the Apache-2.0 license. That permits commercial use, modification, redistribution, and private deployment, as long as you keep the license and attribution notices. You can fine-tune it and ship it inside your own products without a separate agreement.