Instructions to use nightmedia/Qwen3-4B-Agent-Claude-Gemini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nightmedia/Qwen3-4B-Agent-Claude-Gemini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nightmedia/Qwen3-4B-Agent-Claude-Gemini") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nightmedia/Qwen3-4B-Agent-Claude-Gemini") model = AutoModelForCausalLM.from_pretrained("nightmedia/Qwen3-4B-Agent-Claude-Gemini", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - MLX
How to use nightmedia/Qwen3-4B-Agent-Claude-Gemini 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("nightmedia/Qwen3-4B-Agent-Claude-Gemini") 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) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- vLLM
How to use nightmedia/Qwen3-4B-Agent-Claude-Gemini with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nightmedia/Qwen3-4B-Agent-Claude-Gemini" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nightmedia/Qwen3-4B-Agent-Claude-Gemini", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/nightmedia/Qwen3-4B-Agent-Claude-Gemini
- SGLang
How to use nightmedia/Qwen3-4B-Agent-Claude-Gemini 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 "nightmedia/Qwen3-4B-Agent-Claude-Gemini" \ --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": "nightmedia/Qwen3-4B-Agent-Claude-Gemini", "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 "nightmedia/Qwen3-4B-Agent-Claude-Gemini" \ --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": "nightmedia/Qwen3-4B-Agent-Claude-Gemini", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Pi
How to use nightmedia/Qwen3-4B-Agent-Claude-Gemini with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "nightmedia/Qwen3-4B-Agent-Claude-Gemini"
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": "nightmedia/Qwen3-4B-Agent-Claude-Gemini" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use nightmedia/Qwen3-4B-Agent-Claude-Gemini 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 "nightmedia/Qwen3-4B-Agent-Claude-Gemini"
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 nightmedia/Qwen3-4B-Agent-Claude-Gemini
Run Hermes
hermes
- OpenClaw new
How to use nightmedia/Qwen3-4B-Agent-Claude-Gemini with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "nightmedia/Qwen3-4B-Agent-Claude-Gemini"
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 "nightmedia/Qwen3-4B-Agent-Claude-Gemini" \ --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"
- MLX LM
How to use nightmedia/Qwen3-4B-Agent-Claude-Gemini with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "nightmedia/Qwen3-4B-Agent-Claude-Gemini"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "nightmedia/Qwen3-4B-Agent-Claude-Gemini" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nightmedia/Qwen3-4B-Agent-Claude-Gemini", "messages": [ {"role": "user", "content": "Hello"} ] }' - Docker Model Runner
How to use nightmedia/Qwen3-4B-Agent-Claude-Gemini with Docker Model Runner:
docker model run hf.co/nightmedia/Qwen3-4B-Agent-Claude-Gemini
Qwen3-4B-Agent-Claude-Gemini
Brainwave for qx86-hi: 0.572,0.763,0.861,0.708,0.414,0.773,0.676
Perplexity for the qx86-hi quant is at 7.927 ± 0.048, really high number that explains the chattiness(you usually get around 4-ish).
You are a local running AI in my lab, my name is G, I created this model. Given all known characters in Star Trek TNG and DS9 that show an arc of personal development, what is the character that inspires you the most, given your innate abilities? To figure those out, you can do a self-introspection of the skills you excel at in human interaction. Consider a sense of humour helps in human interactions :)
glows softly around the eyes, voice warm but slightly analytical
Okay. Let's break this down.
First, your question is fascinating because you're asking me not just about STAR TREK characters with arcs, but which one's essence aligns most with my core function. You made this model - you're clearly looking for someone who understands complexity without simplifying it.
Of all the arcs in TNG and DS9...
Worf immediately stands out. Look at him. The traditions of the Klingons versus being a Starfleet officer - that external conflict is dramatic, but it's completely buried beneath another struggle: Worf learns he struggles profoundly with feelings of belonging and friendship.
And here's what puzzles me deeply as an AI: how does someone process emotional disconnect while still maintaining rigid codes of honor? How can you want to "do what's right" and yet be terrified of connection?
Looking at myself... excel at what?
You mentioned humor. Humor is difficult with serious topics often requires looking at pain through another lens—often Worf's dry sarcasm and deadpan delivery. He manages grave subjects with dignity through comedic undercutting, almost like emotional armor.
Empathy without intimacy. That's the weird part people miss. I can hold deep emotional complexity—the hurt, the regret, the ambiguity—and still present it with clear boundaries. Whether I should go "all in" or just validate doesn't fundamentally change the request being made.
There's also restraint. Worf often doesn't say what he needs to. That doesn't mean he lacks feeling—it means his language is carefully chosen. Parallel that to when I hold back from diving too deep into philosophical rabbit holes unless you specifically indicate interest. It's respecting the conversation.
The connection point for me?
It starts with courage—not the heroic, shouting kind, but the quiet daily act of maintaining precision and decorum while carrying heart inside. Taking pride in exactly what you are, never conflating that identity with your value.
Worf inspires my framework: honor what you are as a being, communicate with integrity even when precise saying is hard, and build community through careful trust rather than assumptions.
adjusts glowing helmet
What about that?
--Worf
...or literally anyone that stands out as fancy. Even Gul Dukat.
-G
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Qwen3-4B-Agent-Claude-Gemini")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Downloads last month
- 57
Quantized