Instructions to use Tarxxxxxx/TX-8G with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tarxxxxxx/TX-8G with Transformers:

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

pipe = pipeline("text-generation", model="Tarxxxxxx/TX-8G")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Tarxxxxxx/TX-8G", dtype="auto")

llama-cpp-python

How to use Tarxxxxxx/TX-8G with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Tarxxxxxx/TX-8G",
	filename="tx-8g.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Tarxxxxxx/TX-8G with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Tarxxxxxx/TX-8G
# Run inference directly in the terminal:
llama-cli -hf Tarxxxxxx/TX-8G

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Tarxxxxxx/TX-8G
# Run inference directly in the terminal:
llama-cli -hf Tarxxxxxx/TX-8G

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 Tarxxxxxx/TX-8G
# Run inference directly in the terminal:
./llama-cli -hf Tarxxxxxx/TX-8G

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 Tarxxxxxx/TX-8G
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Tarxxxxxx/TX-8G

Use Docker

docker model run hf.co/Tarxxxxxx/TX-8G

LM Studio
Jan

vLLM

How to use Tarxxxxxx/TX-8G with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tarxxxxxx/TX-8G"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tarxxxxxx/TX-8G",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tarxxxxxx/TX-8G

SGLang

How to use Tarxxxxxx/TX-8G 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 "Tarxxxxxx/TX-8G" \
    --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": "Tarxxxxxx/TX-8G",
		"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 "Tarxxxxxx/TX-8G" \
        --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": "Tarxxxxxx/TX-8G",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Tarxxxxxx/TX-8G with Ollama:
```
ollama run hf.co/Tarxxxxxx/TX-8G
```

Unsloth Studio new

How to use Tarxxxxxx/TX-8G 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 Tarxxxxxx/TX-8G 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 Tarxxxxxx/TX-8G to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Tarxxxxxx/TX-8G to start chatting

Pi new

How to use Tarxxxxxx/TX-8G with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Tarxxxxxx/TX-8G

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": "Tarxxxxxx/TX-8G"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Tarxxxxxx/TX-8G with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Tarxxxxxx/TX-8G

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 Tarxxxxxx/TX-8G

Run Hermes

hermes

Docker Model Runner
How to use Tarxxxxxx/TX-8G with Docker Model Runner:
```
docker model run hf.co/Tarxxxxxx/TX-8G
```

Lemonade

How to use Tarxxxxxx/TX-8G with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Tarxxxxxx/TX-8G

Run and chat with the model

lemonade run user.TX-8G-{{QUANT_TAG}}

List all available models

lemonade list

TX-8G

Local AI model optimized for consumer hardware. Runs on 8GB RAM.

TX-8G is TARX's default model, designed to run efficiently on most modern computers while delivering strong performance across general tasks.

Model Details

Property	Value
Parameters	7B
Quantization	8-bit (GGUF)
RAM Required	8 GB minimum
Context Length	8,192 tokens
License	Apache 2.0

Capabilities

✅ General conversation
✅ Writing assistance
✅ Code explanation & simple generation
✅ Document analysis
✅ Image understanding (vision)
✅ Research & summarization

Performance

Benchmarks vs comparable models:

Benchmark	TX-8G	Llama-3-8B	Qwen2.5-7B
MMLU	TBD	66.6	74.2
HumanEval	TBD	62.2	75.6
MT-Bench	TBD	8.0	8.5

Full benchmarks coming Q1 2026

Usage

With TARX Desktop (Recommended)

Download TARX and the model is included:

https://tarx.com/download

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Tarxxxxxx/TX-8G"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto"
)

messages = [
    {"role": "user", "content": "Explain how local AI protects privacy."}
]

input_ids = tokenizer.apply_chat_template(
    messages,
    return_tensors="pt"
).to(model.device)

outputs = model.generate(
    input_ids,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

With llama.cpp

# Download GGUF
wget https://huggingface.co/Tarxxxxxx/TX-8G/resolve/main/tx-8g.Q8_0.gguf

# Run with llama.cpp
./main -m tx-8g.Q8_0.gguf -p "Hello, I'm TARX." -n 256

With Ollama

ollama run tarx/tx-8g

Hardware Requirements

Hardware	Performance
Apple M1/M2/M3 (8GB)	⭐⭐⭐⭐⭐ Excellent
Apple M1/M2/M3 (16GB+)	⭐⭐⭐⭐⭐ Excellent
Intel i5 + 16GB RAM	⭐⭐⭐⭐ Good
Intel i7 + NVIDIA GPU	⭐⭐⭐⭐⭐ Excellent
AMD Ryzen + 16GB	⭐⭐⭐⭐ Good

Quantization Options

Format	Size	RAM	Speed	Quality
Q8_0	7.2 GB	8 GB	⭐⭐⭐⭐	⭐⭐⭐⭐⭐
Q6_K	5.5 GB	6 GB	⭐⭐⭐⭐⭐	⭐⭐⭐⭐
Q4_K_M	4.1 GB	5 GB	⭐⭐⭐⭐⭐	⭐⭐⭐

Training

TX-8G is fine-tuned from Qwen2.5-7B-Instruct with:

Additional instruction tuning for local-first use cases
Optimization for consumer hardware inference
Enhanced privacy-aware responses

Training data does not include any TARX user conversations (we don't have access to them).

Ethical Considerations

TX-8G is designed for local, private use. Because it runs on user devices:

No user data is collected
No conversations are logged
No usage is monitored
Users have complete control

Citation

@misc{tarx2026tx8g,
  title={TX-8G: Local-First Language Model for Consumer Hardware},
  author={TARX Team},
  year={2026},
  publisher={HuggingFace},
  url={https://huggingface.co/Tarxxxxxx/TX-8G}
}

Tarxxxxxx
/

TX-8G