Instructions to use abenzerps/Nex-N2.5-mini-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abenzerps/Nex-N2.5-mini-MLX-8bit with MLX:

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

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("abenzerps/Nex-N2.5-mini-MLX-8bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use abenzerps/Nex-N2.5-mini-MLX-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "abenzerps/Nex-N2.5-mini-MLX-8bit"

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": "abenzerps/Nex-N2.5-mini-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use abenzerps/Nex-N2.5-mini-MLX-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "abenzerps/Nex-N2.5-mini-MLX-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "abenzerps/Nex-N2.5-mini-MLX-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "abenzerps/Nex-N2.5-mini-MLX-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use abenzerps/Nex-N2.5-mini-MLX-8bit 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 "abenzerps/Nex-N2.5-mini-MLX-8bit"

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 abenzerps/Nex-N2.5-mini-MLX-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use abenzerps/Nex-N2.5-mini-MLX-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "abenzerps/Nex-N2.5-mini-MLX-8bit"

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 "abenzerps/Nex-N2.5-mini-MLX-8bit" \
  --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-8bit / README.md

abenzerps

Add Nex-N2.5-mini MLX 8-bit release

268c650 30 days ago

preview code

Raw History Blame Contribute Delete

1.48 kB

metadata

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

Nex-N2.5-mini MLX — 8-bit

MLX 8-bit conversion of 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

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

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

Source

Model: Nex-N2.5-mini
Source revision: 87420286149d9cce9bd46cd335ef9bda33c37c1b
License: Apache-2.0
Checksums: SHA256SUMS.txt