Instructions to use SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SandLogicTechnologies/Tesslate-UIGEN-T2-7B-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 SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SandLogicTechnologies/Tesslate-UIGEN-T2-7B-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 SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SandLogicTechnologies/Tesslate-UIGEN-T2-7B-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 SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SandLogicTechnologies/Tesslate-UIGEN-T2-7B-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 SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M

SGLang

How to use SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF 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 "SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF" \
    --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": "SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF",
		"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 "SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF" \
        --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": "SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF with Ollama:
```
ollama run hf.co/SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M
```

Unsloth Studio

How to use SandLogicTechnologies/Tesslate-UIGEN-T2-7B-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 SandLogicTechnologies/Tesslate-UIGEN-T2-7B-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 SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF to start chatting

How to use SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF: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": "SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF: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 SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF: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 "SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF: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 SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M
```

Lemonade

How to use SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SandLogicTechnologies/Tesslate-UIGEN-T2-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Tesslate-UIGEN-T2-7B-GGUF-Q4_K_M

List all available models

lemonade list

Tesslate/UIGEN-T2-7B (GGUF Q4) - Sandlogic Lexicons

Model Overview

UIGEN-T2-7B is the latest innovation in the UIGEN model series by Tesslate, engineered specifically for high-quality, design-aware user interface (UI) code generation. Built on the strong foundation of the Qwen2.5-Coder-7B-Instruct model and fine-tuned using PEFT/LoRA (Rank 128), UIGEN-T2 has been trained on a significantly larger dataset of 50,000 annotated UI samples. This enables it to generate not only functional HTML and Tailwind CSS code but also code that aligns with usability, design structure, and modern layout principles.

Model Highlights

Architecture: Based on Qwen2.5-Coder-7B-Instruct (decoder-only transformer)
Quantization Format: GGUF Q4
LoRA Fine-Tuning: PEFT/LoRA (Rank 128), with checkpoints published at each training stage
Training Dataset: 50,000 high-quality UI examples (up from 400 in the previous version)
Code Output: Semantic HTML and utility-first Tailwind CSS
UI-Based Reasoning: Incorporates guidance from a reasoning teacher model to ensure usability and aesthetics
Chat Interface: Improved prompt interaction for seamless developer experience

Intended Use Cases

Recommended Applications

Rapid UI Prototyping
Generate clean, production-ready HTML/Tailwind code from natural language descriptions or wireframes.
Component Generation
Create both standard (buttons, forms, cards) and custom components based on user-defined design goals.
Frontend Development Assistant
Accelerate development by producing baseline layouts and component structures for web interfaces.
Design-to-Code Exploration
Bridge the gap between visual design and code implementation, especially helpful for non-developers or design teams.

Model Integration

This quantized Q4 GGUF version of UIGEN-T2-7B is now part of the Sandlogic Lexicons model zoo. It is optimized for efficient inference on edge and constrained environments, without compromising on code quality or reasoning capability.