Instructions to use TensorFold/Nex-N2.5-mini-MLX-oQ6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TensorFold/Nex-N2.5-mini-MLX-oQ6 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("TensorFold/Nex-N2.5-mini-MLX-oQ6")
config = load_config("TensorFold/Nex-N2.5-mini-MLX-oQ6")

# 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 TensorFold/Nex-N2.5-mini-MLX-oQ6 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TensorFold/Nex-N2.5-mini-MLX-oQ6"

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": "TensorFold/Nex-N2.5-mini-MLX-oQ6"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use TensorFold/Nex-N2.5-mini-MLX-oQ6 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 "TensorFold/Nex-N2.5-mini-MLX-oQ6"

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 TensorFold/Nex-N2.5-mini-MLX-oQ6

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TensorFold/Nex-N2.5-mini-MLX-oQ6 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TensorFold/Nex-N2.5-mini-MLX-oQ6"

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 "TensorFold/Nex-N2.5-mini-MLX-oQ6" \
  --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-MLX-oQ6

File size: 1,327 Bytes

<svg width="1118" height="354" viewBox="0 0 1118 354" fill="none" xmlns="http://www.w3.org/2000/svg">
<path d="M1000.47 204.517L977.244 175.437L949.704 141L949.165 141.652L906.805 194.625L884.304 222.799L883.792 223.451L883.765 223.479L861.237 251.652L846.66 233.399L823.404 204.319L780.559 257.944L758.031 286.117L705 352.468H835.745L845.932 339.741L888.777 286.117L911.305 257.944L911.332 257.916L934.56 286.996L949.139 305.248L986.891 352.468H1117.64C1094.98 323.813 1044.55 260.048 1015.08 222.771L1000.47 204.517Z" fill="black"/>
<path d="M845.932 176.379L869.16 205.459L869.187 205.431L869.727 204.779L892.227 176.605L934.56 123.632L935.099 122.98L957.627 94.808L972.205 113.06L999.744 147.525L1093.41 30.3267L1106.48 13.9454L1117.64 3.25913e-05H986.891L934.372 65.728L911.871 93.872L911.332 94.552L838.845 3.8827L835.747 3.25913e-05H705L845.959 176.351L845.932 176.379Z" fill="black"/>
<path d="M501.499 261.748V221.813H752.03V130.86H501.499V90.9534H751.6L678.9 0H415L415.027 352.701H678.9L751.6 261.748H501.499Z" fill="black"/>
<path d="M281.67 249.173L135.396 153.907V266.272L268.634 353.041H394.921V352.7H394.927V3.05176e-05H281.67V249.173Z" fill="black"/>
<path d="M113.257 103.868L259.532 199.135V86.7694L126.293 3.05176e-05L0.00665283 3.05176e-05V0.34137H0V353.041H113.257L113.257 103.868Z" fill="black"/>
</svg>