---
base_model: nex-agi/Nex-N2.5-mini
base_model_relation: quantized
license: apache-2.0
language:
  - en
  - zh
pipeline_tag: text-generation
library_name: mlx
tags:
  - mlx
  - mlx-lm
  - 8-bit
  - long-context
  - 256k-context
  - moe
---

[![🤗 Model Requests](https://img.shields.io/badge/%F0%9F%A4%97_Model_Requests-Submit_Here-f59e0b?style=for-the-badge&labelColor=1f2937)](https://abenzerps.com/request-a-model/)

# Nex-N2.5-mini MLX — 8-bit

MLX 8-bit conversion of [Nex-N2.5-mini](https://huggingface.co/nex-agi/Nex-N2.5-mini), a sparse MoE language model for local inference, coding, reasoning, and long-context work. The source checkpoint supports a native context length of **262,144 tokens (256K)**.

## Benchmarks

![Nex-N2.5 benchmark results](assets/Nex-N2.5-Benchmark-white.png)

*Benchmark results reported by Nex AI for the original Nex-N2.5 checkpoint and its upstream evaluation setup.*

## Release

| Format | Quantization | Size |
| --- | --- | ---: |
| MLX safetensors | Affine 8-bit, group size 64 | 36.85 GB |

This release contains the text-generation weights and tokenizer. It does not include MTP weights or a vision projector.

## Usage

```bash
pip install -U mlx-lm
mlx_lm.generate \
  --model . \
  --prompt "Explain why reproducible builds matter." \
  --max-tokens 512
```

## Source

- Model: [Nex-N2.5-mini](https://huggingface.co/nex-agi/Nex-N2.5-mini)
- Source revision: [87420286149d9cce9bd46cd335ef9bda33c37c1b](https://huggingface.co/nex-agi/Nex-N2.5-mini/tree/87420286149d9cce9bd46cd335ef9bda33c37c1b)
- License: [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0)
- Checksums: [SHA256SUMS.txt](SHA256SUMS.txt)