---
license: apache-2.0
base_model:
- nex-agi/Nex-N2-Pro
pipeline_tag: text-generation
library_name: transformers
tags:
- qwen3_5_moe
- image-text-to-text
- conversational
- gguf
- moe
- agent
---
# Nex-N2-Pro-GGUF
## Overview
This repository contains the **GGUF** quantized files for **[nex-agi/Nex-N2-Pro](https://huggingface.co/nex-agi/Nex-N2-Pro)**.
- **Original Model:** [nex-agi/Nex-N2-Pro](https://huggingface.co/nex-agi/Nex-N2-Pro)
- **Architecture:** Qwen3.5-397B-A17B
- **License:** Apache 2.0
- **MTP Support:** MTP Donor-[unsloth/Qwen3.5-397B-A17B-MTP-GGUF](https://huggingface.co/unsloth/Qwen3.5-397B-A17B-MTP-GGUF)
| Quant Type | Size | Description |
| :--- | :--- | :--- |
| **IQ1+** | 100 GB | Mixed Precision for Better Quality |
| **IQ2_XS** | 142 GB | Mixed Precision for Better Quality |
| **IQ3_XS** | 185-192 GB | Mixed Precision for Better Quality |
| **IQ3_M** | 198-205 GB | Custom Quantization |
| **IQ4_NL** | 244-256 GB | Custom Quantization |
----
**An agentic model with Agentic Thinking.**
Today, we are officially releasing and open-sourcing our next-generation model, **Nex-N2** — an agent model built for real-world productivity scenarios. With first-tier coding and agentic capabilities, Nex-N2 keeps driving complex, long-horizon tasks forward in real environments to deliver stable, end-to-end results.
Over the past year, a paradigm shift led by Vibe Coding and Harness Engineering has been redefining the limits of LLM agents. From dialogue, to reasoning, to agents that execute long-horizon tasks with environmental feedback, the tasks models must handle keep growing harder, the contexts longer, and the environments more realistic. The core of next-generation model competition is no longer *whether a model can think*, but whether it can reliably and efficiently turn thinking into actions that are executable, verifiable, and iterable.
Rather than treating reasoning, tool use, and environment execution as separate capabilities, Nex-N2 unifies them through an **Agentic Thinking** framework that connects requirement understanding, task planning, code implementation, environmental feedback, evaluation and debugging, and continuous iteration into a single closed loop. The framework has two parts:
- **Adaptive Thinking** lets the model decide on its own when to think and how deeply — executing simple actions quickly while reasoning thoroughly on critical decisions.
- **Coherent Thinking** carries one consistent reasoning paradigm across general reasoning and diverse agentic tasks, staying consistent across tasks and modalities to enable stable capability transfer.
Across real agentic workflows — agentic coding, deep research, tool calling, and terminal execution — Nex-N2 reaches first-tier performance, with substantial gains over the previous-generation Nex-N1 on multiple authoritative benchmarks. In real productivity scenarios such as OpenClaw one-person-company workflows, end-to-end game development, and web and multimodal generation, it likewise demonstrates outstanding usability, robustness, and stability.
---
## Performance
| Benchmark | **Nex-N2-mini** | **Nex-N2-Pro** | GPT-5.5 | Opus 4.7 | Kimi-K2.6 | GLM-5.1 | MiniMax M3 | DeepSeek-V4-Pro |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| **Agent** | | | | | | | | |
| BrowseComp | 74.1 | 83.7 | 84.4 | 79.8 | 83.2 | 79.3 | 83.5 | 83.4 |
| GDPval | 1402 | 1585 | 1769 | 1753 | 1481 | 1535 | - | 1554 |
| Toolathlon | 33.3 | 51.9 | 55.6 | 52.8 | 50.0 | 40.7 | - | 51.8 |
| WildClawBench | 47.7 | 53.5 | 58.2 | 62.2 | - | 48.2 | - | 43.7 |
| WideSearch | 62.0 | 75.6 | - | - | 80.8 | - | - | - |
| TAU3 | 65.9 | 71.1 | - | - | - | 70.6 | - | - |
| **Coding & SWE** | | | | | | | | |
| SWE-Bench Pro | 50.2 | 58.8 | 58.6 | 64.3 | 58.6 | 58.4 | 59.0 | 55.4 |
| Terminal-Bench 2.1 | 60.7 | 75.3 | 83.4 | 69.7 | - | 58.7 | 66.0 | 72.0 |
| DeepSWE | 8.0 | 33.6 | 70 | 54 | 24 | 18 | - | 8 |
| SWE-Bench Verified | 74.4 | 80.8 | 82.9 | 87.6 | 80.2 | - | 80.5 | 80.6 |
| SWE Atlas QnA | 31.5 | 37.9 | 45.4 | 45.2 | - | - | 37.9 | - |
| SWE Atlas RF | 30.0 | 32.9 | 44.8 | 48.6 | - | - | - | - |
| SWE Atlas TW | 23.3 | 40.0 | 42.6 | 38.2 | - | - | 30.8 | - |
| **General & Reasoning** | | | | | | | | |
| GPQA Diamond | 82.6 | 90.7 | 93.6 | 94.2 | 90.5 | 86.2 | - | 90.1 |
| IFEval | 89.1 | 94.0 | - | - | 94.5 | 94.5 | - | 91.9 |
| Apex | 9.4 | 36.5 | - | - | 24.0 | 11.5 | - | 38.3 |

---
## How to Use
These GGUF files are fully compatible with [llama.cpp](https://github.com/ggml-org/llama.cpp) and popular graphical interfaces like **LM Studio**, **Ollama**.
### Example using `llama.cpp` CLI:
```bash
./llama-cli -m nex-n2-pro-Q2_K-00001-of-00023.gguf \
-p "Hello, how are you?" \
-sys "You are a helpful AI" \
-n 4096 \
-c 8192