Instructions to use methil-group/nexus-flash-9B-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use methil-group/nexus-flash-9B-mlx-4bit 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("methil-group/nexus-flash-9B-mlx-4bit")

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)

Transformers

How to use methil-group/nexus-flash-9B-mlx-4bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="methil-group/nexus-flash-9B-mlx-4bit")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("methil-group/nexus-flash-9B-mlx-4bit")
model = AutoModelForMultimodalLM.from_pretrained("methil-group/nexus-flash-9B-mlx-4bit")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use methil-group/nexus-flash-9B-mlx-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "methil-group/nexus-flash-9B-mlx-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "methil-group/nexus-flash-9B-mlx-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/methil-group/nexus-flash-9B-mlx-4bit

SGLang

How to use methil-group/nexus-flash-9B-mlx-4bit with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "methil-group/nexus-flash-9B-mlx-4bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "methil-group/nexus-flash-9B-mlx-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "methil-group/nexus-flash-9B-mlx-4bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "methil-group/nexus-flash-9B-mlx-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use methil-group/nexus-flash-9B-mlx-4bit with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for methil-group/nexus-flash-9B-mlx-4bit to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for methil-group/nexus-flash-9B-mlx-4bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for methil-group/nexus-flash-9B-mlx-4bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="methil-group/nexus-flash-9B-mlx-4bit",
    max_seq_length=2048,
)

How to use methil-group/nexus-flash-9B-mlx-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "methil-group/nexus-flash-9B-mlx-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "methil-group/nexus-flash-9B-mlx-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use methil-group/nexus-flash-9B-mlx-4bit 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 "methil-group/nexus-flash-9B-mlx-4bit"

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 methil-group/nexus-flash-9B-mlx-4bit

Run Hermes

hermes

MLX LM

How to use methil-group/nexus-flash-9B-mlx-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "methil-group/nexus-flash-9B-mlx-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "methil-group/nexus-flash-9B-mlx-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "methil-group/nexus-flash-9B-mlx-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use methil-group/nexus-flash-9B-mlx-4bit with Docker Model Runner:
```
docker model run hf.co/methil-group/nexus-flash-9B-mlx-4bit
```

Nexus-Flash-9B-MLX-4bit

This model is a fine-tuned version of unsloth/Qwen3.5-9B, optimized for agent-based reasoning tasks. It was trained using the Unsloth framework to achieve faster training speeds and memory efficiency.

📋 Model Details

Developed by: ethanzxv
Base Model: unsloth/Qwen3.5-9B
License: Apache-2.0
Language: English
Finetuning Dataset: lambda/hermes-agent-reasoning-traces

🚀 Training & Optimization

This model was trained 2x faster using Unsloth combined with Hugging Face's TRL library. Unsloth allows for efficient fine-tuning of Large Language Models (LLMs) with significantly reduced VRAM usage and increased throughput.

Dataset Information

The model was fine-tuned on the Hermes Agent Reasoning Traces dataset. This dataset focuses on enhancing the model's ability to perform complex reasoning steps, particularly in agentic workflows, by providing detailed traces of thought processes and decision-making paths.

Dataset: lambda/hermes-agent-reasoning-traces

🎯 Intended Use & Capabilities

This model is designed for:

Agent Reasoning: Improved performance in tasks requiring multi-step logical deduction.
Complex Problem Solving: Better handling of intricate queries that require chain-of-thought processing.
General Text Generation: Maintains the strong general capabilities of the base Qwen3.5-9B model.

📄 License

This model is released under the Apache-2.0 license. Please refer to the base model's license and the dataset's license for any additional restrictions or requirements.