Instructions to use CultriX/MergeTrix-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CultriX/MergeTrix-7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CultriX/MergeTrix-7B-GGUF",
	filename="mergetrix-7b.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use CultriX/MergeTrix-7B-GGUF 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 CultriX/MergeTrix-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CultriX/MergeTrix-7B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CultriX/MergeTrix-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CultriX/MergeTrix-7B-GGUF: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 CultriX/MergeTrix-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf CultriX/MergeTrix-7B-GGUF: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 CultriX/MergeTrix-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CultriX/MergeTrix-7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/CultriX/MergeTrix-7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use CultriX/MergeTrix-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CultriX/MergeTrix-7B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CultriX/MergeTrix-7B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CultriX/MergeTrix-7B-GGUF:Q4_K_M

Ollama
How to use CultriX/MergeTrix-7B-GGUF with Ollama:
```
ollama run hf.co/CultriX/MergeTrix-7B-GGUF:Q4_K_M
```

Unsloth Studio

How to use CultriX/MergeTrix-7B-GGUF 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 CultriX/MergeTrix-7B-GGUF 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 CultriX/MergeTrix-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CultriX/MergeTrix-7B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use CultriX/MergeTrix-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/CultriX/MergeTrix-7B-GGUF:Q4_K_M
```

Lemonade

How to use CultriX/MergeTrix-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CultriX/MergeTrix-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MergeTrix-7B-GGUF-Q4_K_M

List all available models

lemonade list

MergeTrix-7B is a merge of the following models using LazyMergekit:

MergeTrix-7B-GGUF

Quantisized versions of MergeTrix-7B. Supports:

mergetrix-7b.Q4_K_M.gguf (4.37GB): medium, balanced quality
mergetrix-7b.Q5_K_S.gguf (5 GB): large, low quality loss
mergetrix-7b.Q5_K_M.gguf (5.13 GB): large, very low quality loss
mergetrix-7b.Q6_K.gguf (5.94 GB): very large, extremely low quality loss

🧩 Configuration

models:
  - model: udkai/Turdus
    # No parameters necessary for base model
  - model: abideen/NexoNimbus-7B
    parameters:
      density: 0.53
      weight: 0.4
  - model: fblgit/UNA-TheBeagle-7b-v1
    parameters:
      density: 0.53
      weight: 0.3
  - model: argilla/distilabeled-Marcoro14-7B-slerp
    parameters:
      density: 0.53
      weight: 0.3
merge_method: dare_ties
base_model: udkai/Turdus
parameters:
  int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "CultriX/MergeTrix-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: 19

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

6-bit