Instructions to use ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 with Transformers:

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

pipe = pipeline("text-generation", model="ertghiu256/Qwen3-4b-tcomanr-merge-v2.7")
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-v2.7")
model = AutoModelForCausalLM.from_pretrained("ertghiu256/Qwen3-4b-tcomanr-merge-v2.7")
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-v2.7 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-v2.7",
	filename="Tcomanr-V2_7-4.0B-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-v2.7 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ertghiu256/Qwen3-4b-tcomanr-merge-v2.7:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ertghiu256/Qwen3-4b-tcomanr-merge-v2.7:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ertghiu256/Qwen3-4b-tcomanr-merge-v2.7:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ertghiu256/Qwen3-4b-tcomanr-merge-v2.7: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-v2.7:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ertghiu256/Qwen3-4b-tcomanr-merge-v2.7: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-v2.7:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ertghiu256/Qwen3-4b-tcomanr-merge-v2.7:Q4_K_M

Use Docker

docker model run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge-v2.7:Q4_K_M

LM Studio
Jan

vLLM

How to use ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 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-v2.7"
# 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-v2.7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge-v2.7:Q4_K_M

SGLang

How to use ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 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-v2.7" \
    --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-v2.7",
		"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-v2.7" \
        --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-v2.7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 with Ollama:
```
ollama run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge-v2.7:Q4_K_M
```

Unsloth Studio

How to use ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 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-v2.7 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-v2.7 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-v2.7 to start chatting

How to use ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ertghiu256/Qwen3-4b-tcomanr-merge-v2.7: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-v2.7:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ertghiu256/Qwen3-4b-tcomanr-merge-v2.7: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-v2.7:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ertghiu256/Qwen3-4b-tcomanr-merge-v2.7:Q4_K_M

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 "ertghiu256/Qwen3-4b-tcomanr-merge-v2.7:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 with Docker Model Runner:
```
docker model run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge-v2.7:Q4_K_M
```

Lemonade

How to use ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ertghiu256/Qwen3-4b-tcomanr-merge-v2.7:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4b-tcomanr-merge-v2.7-Q4_K_M

List all available models

lemonade list

Qwen3-4b-tcomanr-merge-v2.7 / README.md

ertghiu256

Upload folder using huggingface_hub

363736a verified 7 months ago

preview code

Raw

History Blame

5.11 kB

	---
	base_model:
	- janhq/Jan-v1-4B
	- Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2
	- POLARIS-Project/Polaris-4B-Preview
	- ertghiu256/qwen3-math-reasoner
	- Tesslate/UIGEN-FX-4B-Preview
	- quelmap/Lightning-4b
	- rex099/Human-Like-DPO-Qwen3-4B-Instruct-2507
	- ValiantLabs/Qwen3-4B-ShiningValiant3
	- GetSoloTech/Qwen3-Code-Reasoning-4B
	- ertghiu256/Qwen3-4B-Thinking-2507-Hermes-3
	- Qwen/Qwen3-4b-Instruct-2507
	- ertghiu256/Qwen3-Hermes-4b
	- ertghiu256/qwen3-4b-mixture-of-thought-v2
	- Tesslate/WEBGEN-4B-Preview
	- ertghiu256/Qwen3-4b-2507-Thinking-math-and-code
	- huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated
	- Qwen/Qwen3-4B-Thinking-2507
	- ValiantLabs/Qwen3-4B-Esper3
	- ertghiu256/qwen3-multi-reasoner
	- ertghiu256/qwen3-4b-code-reasoning
	library_name: transformers
	tags:
	- mergekit
	- merge

	---
	# Tcomanr-V2_7

	This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

	## Merge Details
	### Merge Method

	This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen3-4b-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4b-Instruct-2507) as a base.

	### Models Merged

	The following models were included in the merge:
	* [janhq/Jan-v1-4B](https://huggingface.co/janhq/Jan-v1-4B)
	* [Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2](https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2)
	* [POLARIS-Project/Polaris-4B-Preview](https://huggingface.co/POLARIS-Project/Polaris-4B-Preview)
	* [ertghiu256/qwen3-math-reasoner](https://huggingface.co/ertghiu256/qwen3-math-reasoner)
	* [Tesslate/UIGEN-FX-4B-Preview](https://huggingface.co/Tesslate/UIGEN-FX-4B-Preview)
	* [quelmap/Lightning-4b](https://huggingface.co/quelmap/Lightning-4b)
	* [rex099/Human-Like-DPO-Qwen3-4B-Instruct-2507](https://huggingface.co/rex099/Human-Like-DPO-Qwen3-4B-Instruct-2507)
	* [ValiantLabs/Qwen3-4B-ShiningValiant3](https://huggingface.co/ValiantLabs/Qwen3-4B-ShiningValiant3)
	* [GetSoloTech/Qwen3-Code-Reasoning-4B](https://huggingface.co/GetSoloTech/Qwen3-Code-Reasoning-4B)
	* [ertghiu256/Qwen3-4B-Thinking-2507-Hermes-3](https://huggingface.co/ertghiu256/Qwen3-4B-Thinking-2507-Hermes-3)
	* [ertghiu256/Qwen3-Hermes-4b](https://huggingface.co/ertghiu256/Qwen3-Hermes-4b)
	* [ertghiu256/qwen3-4b-mixture-of-thought-v2](https://huggingface.co/ertghiu256/qwen3-4b-mixture-of-thought-v2)
	* [Tesslate/WEBGEN-4B-Preview](https://huggingface.co/Tesslate/WEBGEN-4B-Preview)
	* [ertghiu256/Qwen3-4b-2507-Thinking-math-and-code](https://huggingface.co/ertghiu256/Qwen3-4b-2507-Thinking-math-and-code)
	* [huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated](https://huggingface.co/huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated)
	* [Qwen/Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507)
	* [ValiantLabs/Qwen3-4B-Esper3](https://huggingface.co/ValiantLabs/Qwen3-4B-Esper3)
	* [ertghiu256/qwen3-multi-reasoner](https://huggingface.co/ertghiu256/qwen3-multi-reasoner)
	* [ertghiu256/qwen3-4b-code-reasoning](https://huggingface.co/ertghiu256/qwen3-4b-code-reasoning)

	### Configuration

	The following YAML configuration was used to produce this model:

	```yaml
	models:
	- model: ertghiu256/qwen3-math-reasoner
	parameters:
	weight: 0.85
	- model: ertghiu256/qwen3-4b-code-reasoning
	parameters:
	weight: 0.9
	- model: ertghiu256/qwen3-4b-mixture-of-thought-v2
	parameters:
	weight: 1.0
	- model: POLARIS-Project/Polaris-4B-Preview
	parameters:
	weight: 0.95
	- model: ertghiu256/qwen3-multi-reasoner
	parameters:
	weight: 0.8
	- model: ertghiu256/Qwen3-Hermes-4b
	parameters:
	weight: 0.6
	- model: ValiantLabs/Qwen3-4B-Esper3
	parameters:
	weight: 0.7
	- model: Tesslate/WEBGEN-4B-Preview
	parameters:
	weight: 0.85
	- model: Tesslate/UIGEN-FX-4B-Preview
	parameters:
	weight: 0.9
	- model: ValiantLabs/Qwen3-4B-ShiningValiant3
	parameters:
	weight: 0.7
	- model: huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated
	parameters:
	weight: 0.75
	- model: Qwen/Qwen3-4B-Thinking-2507
	parameters:
	weight: 1.0
	- model: Qwen/Qwen3-4b-Instruct-2507
	parameters:
	weight: 1.4
	- model: GetSoloTech/Qwen3-Code-Reasoning-4B
	parameters:
	weight: 1.0
	- model: ertghiu256/Qwen3-4B-Thinking-2507-Hermes-3
	parameters:
	weight: 1.0
	- model: janhq/Jan-v1-4B
	parameters:
	weight: 0.2
	- model: Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2
	parameters:
	weight: 0.7
	- model: quelmap/Lightning-4b
	parameters:
	weight: 0.6
	- model: ertghiu256/Qwen3-4b-2507-Thinking-math-and-code
	parameters:
	weight: 0.9
	- model: rex099/Human-Like-DPO-Qwen3-4B-Instruct-2507
	parameters:
	weight: 0.75
	merge_method: ties
	base_model: Qwen/Qwen3-4b-Instruct-2507
	parameters:
	normalize: true
	int8_mask: true
	lambda: 1.0
	dtype: float16
	```