Instructions to use vicharai/ViCoder-html-32B-preview-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vicharai/ViCoder-html-32B-preview-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="vicharai/ViCoder-html-32B-preview-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vicharai/ViCoder-html-32B-preview-GGUF", dtype="auto")

llama-cpp-python

How to use vicharai/ViCoder-html-32B-preview-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vicharai/ViCoder-html-32B-preview-GGUF",
	filename="ViCoder-32B-Q3_K_M.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 vicharai/ViCoder-html-32B-preview-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vicharai/ViCoder-html-32B-preview-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 vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vicharai/ViCoder-html-32B-preview-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 vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M

Use Docker

docker model run hf.co/vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use vicharai/ViCoder-html-32B-preview-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vicharai/ViCoder-html-32B-preview-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": "vicharai/ViCoder-html-32B-preview-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M

SGLang

How to use vicharai/ViCoder-html-32B-preview-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 "vicharai/ViCoder-html-32B-preview-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": "vicharai/ViCoder-html-32B-preview-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 "vicharai/ViCoder-html-32B-preview-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": "vicharai/ViCoder-html-32B-preview-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use vicharai/ViCoder-html-32B-preview-GGUF with Ollama:
```
ollama run hf.co/vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M
```

Unsloth Studio new

How to use vicharai/ViCoder-html-32B-preview-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 vicharai/ViCoder-html-32B-preview-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 vicharai/ViCoder-html-32B-preview-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vicharai/ViCoder-html-32B-preview-GGUF to start chatting

Pi new

How to use vicharai/ViCoder-html-32B-preview-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf vicharai/ViCoder-html-32B-preview-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": "vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use vicharai/ViCoder-html-32B-preview-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf vicharai/ViCoder-html-32B-preview-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 vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use vicharai/ViCoder-html-32B-preview-GGUF with Docker Model Runner:
```
docker model run hf.co/vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M
```

Lemonade

How to use vicharai/ViCoder-html-32B-preview-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vicharai/ViCoder-html-32B-preview-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ViCoder-html-32B-preview-GGUF-Q4_K_M

List all available models

lemonade list

VICODER HTML 32B PREVIEW QUANTIZATIONS

Overview

ViCoder-HTML-32B-preview is a powerful AI model designed to generate full websites, including HTML, Tailwind CSS, and JavaScript.

Model Quantizations

This model comes in several quantizations, each offering a balance of file size and performance. Choose the one that best suits your memory and quality requirements.

Quantization	Size (GB)	Expected Quality	Notes
Q8_0	34.8	🟢 Very good – nearly full precision	8-bit quantization, very close to full precision for most tasks.
Q6_K	26.9	🟢 Good – retains most performance	6-bit quantization, high quality, efficient for most applications.
Q4_K_M	19.9	🟡 Moderate – usable with minor degradation	4-bit quantization, good tradeoff between quality and size.
Q3_K_M	15.9	🟠 Lower – may lose accuracy, better for small RAM	3-bit quantization, lower quality, best for minimal memory use.

Features

Full Website Generation: Generates HTML code with Tailwind CSS and JavaScript for modern, responsive websites.
Flexible Quantization: Choose from various quantization models to fit your hardware and performance requirements.
Ease of Use: The model is easy to integrate using llama.cpp and Ollama