Instructions to use nightmedia/Qwen3-4B-Agent-Eva with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nightmedia/Qwen3-4B-Agent-Eva with Transformers:

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

pipe = pipeline("text-generation", model="nightmedia/Qwen3-4B-Agent-Eva")
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-Eva")
model = AutoModelForCausalLM.from_pretrained("nightmedia/Qwen3-4B-Agent-Eva")
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-Eva 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-Eva")

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
LM Studio

vLLM

How to use nightmedia/Qwen3-4B-Agent-Eva 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-Eva"
# 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-Eva",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nightmedia/Qwen3-4B-Agent-Eva

SGLang

How to use nightmedia/Qwen3-4B-Agent-Eva 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-Eva" \
    --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-Eva",
		"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-Eva" \
        --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-Eva",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Pi new

How to use nightmedia/Qwen3-4B-Agent-Eva 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-Eva"

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-Eva"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nightmedia/Qwen3-4B-Agent-Eva 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-Eva"

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-Eva

Run Hermes

hermes

MLX LM

How to use nightmedia/Qwen3-4B-Agent-Eva 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-Eva"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nightmedia/Qwen3-4B-Agent-Eva"
# 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-Eva",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use nightmedia/Qwen3-4B-Agent-Eva with Docker Model Runner:
```
docker model run hf.co/nightmedia/Qwen3-4B-Agent-Eva
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3-4B-Agent-Eva-qx86-hi-mlx

This is a model merge between Qwen3-4B-Agent and FutureMa/Eva-4B.

Brainwaves of qx86-hi quants of the parent models and Qwen3-4B-Agent-Eva

Agent     0.603,0.817,0.838,0.743,0.426,0.780,0.708
Eva-4B    0.539,0.747,0.864,0.606,0.412,0.751,0.605

Qwen3-4B-Agent-Eva
bf16      0.565,0.779,0.872,0.700,0.418,0.776,0.653
qx86-hi   0.568,0.775,0.872,0.699,0.418,0.777,0.654

The Agent base is abliterated and contains only the essential models to top 0.6/0.8 arc--this level of performance is usually found in much larger models, if at all. Agent has an unforgiving nature, and here with the Eva merge, it will look for accountability :)

The qx86-hi quant performs at the same level with full precision in this model, and lower than the Agent base because Eva came with lower metrics to begin with.

The Element models are profiled to act as agents on the Star Trek DS9 station, in a roleplay scenario.

The models can be used for regular tasks as well.

Each comes with different skills. I found FutureMa/Eva-4B recently with an interesting model card: