Instructions to use ertghiu256/Qwen3-4b-tcomanr-merge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ertghiu256/Qwen3-4b-tcomanr-merge with Transformers:

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

pipe = pipeline("text-generation", model="ertghiu256/Qwen3-4b-tcomanr-merge")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ertghiu256/Qwen3-4b-tcomanr-merge")
model = AutoModelForCausalLM.from_pretrained("ertghiu256/Qwen3-4b-tcomanr-merge")
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]:]))

llama-cpp-python

How to use ertghiu256/Qwen3-4b-tcomanr-merge with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ertghiu256/Qwen3-4b-tcomanr-merge",
	filename="model-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ertghiu256/Qwen3-4b-tcomanr-merge with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M

Use Docker

docker model run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M

LM Studio
Jan

vLLM

How to use ertghiu256/Qwen3-4b-tcomanr-merge with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ertghiu256/Qwen3-4b-tcomanr-merge"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ertghiu256/Qwen3-4b-tcomanr-merge",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M

SGLang

How to use ertghiu256/Qwen3-4b-tcomanr-merge 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 "ertghiu256/Qwen3-4b-tcomanr-merge" \
    --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": "ertghiu256/Qwen3-4b-tcomanr-merge",
		"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 "ertghiu256/Qwen3-4b-tcomanr-merge" \
        --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": "ertghiu256/Qwen3-4b-tcomanr-merge",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ertghiu256/Qwen3-4b-tcomanr-merge with Ollama:
```
ollama run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M
```

Unsloth Studio

How to use ertghiu256/Qwen3-4b-tcomanr-merge 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 ertghiu256/Qwen3-4b-tcomanr-merge 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 ertghiu256/Qwen3-4b-tcomanr-merge to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ertghiu256/Qwen3-4b-tcomanr-merge to start chatting

How to use ertghiu256/Qwen3-4b-tcomanr-merge with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ertghiu256/Qwen3-4b-tcomanr-merge with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M

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 ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use ertghiu256/Qwen3-4b-tcomanr-merge with Docker Model Runner:
```
docker model run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M
```

Lemonade

How to use ertghiu256/Qwen3-4b-tcomanr-merge with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4b-tcomanr-merge-Q4_K_M

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A newer version of this model is available: ertghiu256/Qwen3-4b-tcomanr-merge-v2.5

Ties merged COde MAth aNd Reasoning model

This is a merge of pre-trained language models created using mergekit.

Merge Details

This model aims to combine the code and math capabilities by merging multiple Qwen 3 finetunes.

How to run

You can run this model by using multiple interface choices

transformers

As the qwen team suggested to use

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "ertghiu256/Qwen3-4b-tcomanr-merge"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

vllm

Run this command

vllm serve ertghiu256/Qwen3-4b-tcomanr-merge --enable-reasoning --reasoning-parser deepseek_r1

Sglang

Run this command

python -m sglang.launch_server --model-path ertghiu256/Qwen3-4b-tcomanr-merge --reasoning-parser deepseek-r1

llama.cpp

Run this command

llama-server --hf-repo ertghiu256/Qwen3-4b-tcomanr-merge

llama-cli --hf ertghiu256/Qwen3-4b-tcomanr-merge

ollama

Run this command

ollama run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge:Q4_K_M

lm studio

ertghiu256/Qwen3-4b-tcomanr-merge

in the lm studio model search list then download

Recomended parameters

temp: 0.6
num_ctx: ≥8192
top_p: 0.95
top_k: 10

Merge Details

This model was merged using the TIES merge method using Qwen/Qwen3-4B as a base.

Models:

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ertghiu256/qwen3-math-reasoner
    parameters:
      weight: 0.7
  - model: ertghiu256/qwen3-4b-code-reasoning
    parameters:
      weight: 0.8
  - model: ertghiu256/qwen-3-4b-mixture-of-thought
    parameters:
      weight: 0.9
  - model: POLARIS-Project/Polaris-4B-Preview
    parameters:
      weight: 0.7
  - model: ertghiu256/qwen3-multi-reasoner
    parameters:
      weight: 0.8
  - model: ValiantLabs/Qwen3-4B-Esper3
    parameters:
      weight: 0.8
  - model: Tesslate/UIGEN-T3-4B-Preview-MAX
    parameters:
      weight: 0.8
  - model: ValiantLabs/Qwen3-4B-ShiningValiant3
    parameters:
      weight: 0.9
  - model: prithivMLmods/Crux-Qwen3_OpenThinking-4B
    parameters:
      weight: 0.4
merge_method: ties
base_model: Qwen/Qwen3-4B
parameters:
  normalize: true
  int8_mask: true
dtype: float16