---
title: Nex-N2.6
canonical_url: "https://www.modelscope.ai/models/nex-agi/Nex-N2.6"
md_url: "https://www.modelscope.ai/models/nex-agi/Nex-N2.6.md"
repository: nex-agi/Nex-N2.6
last_updated: 2026-11-12
license: apache-2.0
model_type:
- glm5_next
architectures:
- Glm5NextForConditionalGeneration
parameters: 321.3B
tensor_type:
- F8_E4M3
- BF16
- F32
library_name:
- safetensors
- pytorch
frameworks:
- pytorch
downloads: 10
stars: 0
---
# Nex-N2.6
> Nex-N2.6 - An open-source model by nex-agi on ModelScope. Nex-N2.6 is a multimodal agentic model from Nex-AGI, built on GLM-5.3-Flash. It is designed for computer use, coding, and long-horizon tasks involving tools. This repository contains the FP8-quantized…
nex-agi/Nex-N2.6 is a 321.3B-parameter machine learning model on ModelScope. licensed under apache-2.0.
- **Repository**: nex-agi/Nex-N2.6
- **License**: apache-2.0
- **Parameters**: 321.3B
- **Downloads**: 10
- **Stars**: 0
- **Last updated**: 2026-11-12
Source: https://www.modelscope.ai/models/nex-agi/Nex-N2.6
---
Nex-N2.6
API 👉 OpenRouter
Nex-N2.6 is a multimodal agentic model from Nex-AGI, built on [GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash-BF16). It is designed for computer use, coding, and long-horizon tasks involving tools. This repository contains the FP8-quantized weights of Nex-N2.6, with approximately 321B parameters.
Following [Nex-N2.5-Pro](https://huggingface.co/nex-agi/Nex-N2.5-Pro), this release focuses on reducing repetitive reasoning and improving adherence to the tools available in the current environment.
## Highlights
- 🔥 **Less repetitive reasoning:** Reasoning repetition fell from 16.0% to 1.6% compared with Nex-N2.5-Pro in our internal checkpoint-replay evaluation—a 90% relative reduction.
- 🛠️ **Improved tool-list adherence:** Nex-N2.6 achieved 100% tool-list adherence among responses making tool calls in our internal evaluation.
- 🖥️ **Stronger computer use:** Nex-N2.6 scored 83.0 on OSWorld, up from 82.2 for Nex-N2.5-Pro and 78.0 for the base model, GLM-5.3-Flash.
## Performance
The following results are reported by the Nex-AGI team for this release. Scores depend on the evaluation harness and settings. These are model-level results, not a separate evaluation of this FP8 export.
| Benchmark ↑ | GLM-5.3-Flash | DeepSeek-V4.1-Flash | Nex-N2.5-Pro | Nex-N2.6 |
| --- | ---: | ---: | ---: | ---: |
| OSWorld | 78.0 | 71.7 | 82.2 | **83.0** |
| Terminal-Bench 2.1 | 84.3 | 82.7 | 82.7 | 84.1 |
| AutomationBench | 48.8 | 54.8 | 44.2 | 45.7 |
### Internal reliability evaluations
These evaluations are built from issues encountered in real tasks by our team and partner teams. Known-issue replay fixes the preceding conversation and tool outputs, then tests the model's next response. Tool-list adherence checks whether generated calls use only the tools declared in the request.
| Metric | Nex-N2.5-Pro | GLM-5.3-Flash | Nex-N2.6 |
| --- | ---: | ---: | ---: |
| Reasoning Repetition Rate ↓ | 16.0% | 6.0% | **1.6%** |
| Overall Non-Repetition Rate ↑ | 91.0% | 96.2% | **97.8%** |
| Valid Tool Selection Rate (Overall) ↑ | 82.2% | 85.3% | **100.0%** |
| Valid Tool Selection Rate (When with Tools) ↑ | 80.5% | 84.1% | **100.0%** |
## Usage
Use an inference runtime with GLM-5.3-Flash support. For self-hosting, follow the [official SGLang deployment guide](https://github.com/sgl-project/sglang/blob/main/docs/cookbook/autoregressive/GLM/GLM-5.3-Flash.mdx) and select an **FP8-compatible** configuration for your hardware. Replace the model path with the downloaded Nex-N2.6 directory and set `--served-model-name Nex-N2.6`. Keep the tokenizer, processor, and chat template shipped with these weights.
Once the OpenAI-compatible server is listening on port 8000:
```bash
curl -N http://localhost:8000/v1/chat/completions \
-H 'Content-Type: application/json' \
-d '{
"model": "Nex-N2.6",
"messages": [
{"role": "user", "content": "Write a Python function that checks whether a string is a palindrome."}
],
"reasoning_effort": "max",
"max_tokens": 8192,
"stream": true
}'
```
The bundled chat template supports `reasoning_effort` values `low`, `high`, and `max`, defaulting to `max`. For image inputs, use image content blocks supported by your serving runtime. For tool use, supply the available tools with each request; the client or agent framework executes tool calls and returns their results.
## Community
Join the Nex community to share feedback, discuss agent workflows, and connect with other developers.
| Feishu / Lark | WeChat |
| :---: | :---: |
| 
| 
|