Instructions to use suzu89/Nex-N2.5-mini-oQ5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use suzu89/Nex-N2.5-mini-oQ5 with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("suzu89/Nex-N2.5-mini-oQ5")
config = load_config("suzu89/Nex-N2.5-mini-oQ5")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use suzu89/Nex-N2.5-mini-oQ5 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "suzu89/Nex-N2.5-mini-oQ5"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "suzu89/Nex-N2.5-mini-oQ5"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use suzu89/Nex-N2.5-mini-oQ5 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "suzu89/Nex-N2.5-mini-oQ5"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default suzu89/Nex-N2.5-mini-oQ5

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use suzu89/Nex-N2.5-mini-oQ5 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "suzu89/Nex-N2.5-mini-oQ5"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "suzu89/Nex-N2.5-mini-oQ5" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Nex-N2.5-mini-oQ5

Unofficial MLX quantization of nex-agi/Nex-N2.5-mini for Apple Silicon. The upstream model is a multimodal mixture-of-experts model; this repository contains MLX safetensors, not GGUF or PyTorch weights. I am not affiliated with Nex AGI.

What is in this repository

Property	Value
Architecture	Qwen3_5MoeForConditionalGeneration
Quantization	affine, group size 64; 5-bit default with 6-bit and 8-bit module overrides
Weight size	23.57 GiB (25.30 GB), 5 safetensors shards
Text model	40 layers, 256 experts, 8 experts selected per token
Vision	vision tensors retained in BF16
Context limit in config	262,144 tokens; usable context depends on available memory
MTP	not present (mtp_num_hidden_layers: 0)

The numbers above were read from the shipped config.json, model.safetensors.index.json and safetensors headers. The five shards contain 2,010 indexed tensors. The quantization recipe is recorded in config.json so a compatible MLX loader can reconstruct the per-module precision.

This conversion has not been benchmarked against the upstream BF16 model. The upstream benchmark figures on its model card are not results for these quantized weights. Quantization can change output quality, and memory use grows with context length and cache settings.

Usage

Download the model into your oMLX model directory:

hf download suzu89/Nex-N2.5-mini-oQ5 --local-dir ~/.omlx/models/Nex-N2.5-mini-oQ5
omlx serve --model-dir ~/.omlx/models --port 8000

Use the model ID Nex-N2.5-mini-oQ5 in oMLX. This architecture includes a vision tower, so use an MLX runtime with Qwen3.5 MoE multimodal support. The 262k context value is an architecture limit, not a promise that it will fit in memory.

License and attribution

The upstream repository declares Apache License 2.0. This repository includes the license text and a notice identifying the source and the quantization change. The upstream model and its reported evaluations belong to Nex AGI.

Citation

@misc{nex-n25-mini-oq5,
  title = {Nex-N2.5-mini-oQ5: MLX quantization of Nex-N2.5-mini},
  author = {suzu89},
  year = {2026},
  url = {https://huggingface.co/suzu89/Nex-N2.5-mini-oQ5},
  note = {Unofficial quantization of nex-agi/Nex-N2.5-mini}
}

Downloads last month: -

Safetensors

Model size

35B params

Tensor type

U32

BF16

MLX

Hardware compatibility

5-bit

Model tree for suzu89/Nex-N2.5-mini-oQ5

Base model

nex-agi/Nex-N2.5-mini

Quantized

(36)

this model