Instructions to use uaytug/uCoder-8b-base-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uaytug/uCoder-8b-base-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="uaytug/uCoder-8b-base-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("uaytug/uCoder-8b-base-GGUF", dtype="auto")

llama-cpp-python

How to use uaytug/uCoder-8b-base-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="uaytug/uCoder-8b-base-GGUF",
	filename="uCoder-8b-base-BF16.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 uaytug/uCoder-8b-base-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf uaytug/uCoder-8b-base-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf uaytug/uCoder-8b-base-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 uaytug/uCoder-8b-base-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf uaytug/uCoder-8b-base-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 uaytug/uCoder-8b-base-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf uaytug/uCoder-8b-base-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 uaytug/uCoder-8b-base-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf uaytug/uCoder-8b-base-GGUF:Q4_K_M

Use Docker

docker model run hf.co/uaytug/uCoder-8b-base-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use uaytug/uCoder-8b-base-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "uaytug/uCoder-8b-base-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": "uaytug/uCoder-8b-base-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/uaytug/uCoder-8b-base-GGUF:Q4_K_M

SGLang

How to use uaytug/uCoder-8b-base-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 "uaytug/uCoder-8b-base-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": "uaytug/uCoder-8b-base-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 "uaytug/uCoder-8b-base-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": "uaytug/uCoder-8b-base-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use uaytug/uCoder-8b-base-GGUF with Ollama:
```
ollama run hf.co/uaytug/uCoder-8b-base-GGUF:Q4_K_M
```

Unsloth Studio new

How to use uaytug/uCoder-8b-base-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 uaytug/uCoder-8b-base-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 uaytug/uCoder-8b-base-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for uaytug/uCoder-8b-base-GGUF to start chatting

Pi new

How to use uaytug/uCoder-8b-base-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf uaytug/uCoder-8b-base-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": "uaytug/uCoder-8b-base-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use uaytug/uCoder-8b-base-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 uaytug/uCoder-8b-base-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 uaytug/uCoder-8b-base-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use uaytug/uCoder-8b-base-GGUF with Docker Model Runner:
```
docker model run hf.co/uaytug/uCoder-8b-base-GGUF:Q4_K_M
```

Lemonade

How to use uaytug/uCoder-8b-base-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull uaytug/uCoder-8b-base-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.uCoder-8b-base-GGUF-Q4_K_M

List all available models

lemonade list

uCoder-8b-base-GGUF

Quantized GGUF models converted from uaytug/uCoder-8b-base.

Converted using the latest llama.cpp (CUDA-accelerated quantization).

Available Files

16-bit

uCoder-8b-base-BF16.gguf → Highest precision float (similar to original, ~16 GB)

8-bit

uCoder-8b-base-Q8_0.gguf → Near-lossless

6-bit

uCoder-8b-base-Q6_K.gguf

5-bit

uCoder-8b-base-Q5_K_S.gguf
uCoder-8b-base-Q5_K_M.gguf → Great quality

4-bit (most popular range)

uCoder-8b-base-Q4_K_M.gguf → Recommended balance
uCoder-8b-base-Q4_K_S.gguf
uCoder-8b-base-Q4_1.gguf

3-bit

uCoder-8b-base-Q3_K_S.gguf
uCoder-8b-base-Q3_K_M.gguf

2-bit

uCoder-8b-base-Q2_K.gguf

Original Model Information

uCoder-8b-base

uCoder-8b-base is a coding-specialized 8B parameter model created by TIES-merging five high-quality distilled models based on Qwen3-8B. This merge is designed to combine advanced reasoning capabilities with state-of-the-art coding performance, making it an ideal base for further instruction tuning or direct code generation tasks.

🚀 Model Description

This model leverages the TIES (Trimming, Electing, and Signs) merging method to effectively combine the weights of multiple expert models without losing the specific competencies of each. By normalizing the weights and focusing on high-reasoning distillations from top-tier frontier models (GPT-5.x, Claude 4.5, etc.), uCoder-8b-base achieves a robust balance between logic and syntax accuracy.

Key Features

High Reasoning: Inherits logic handling from Claude and GPT-based distills.
Polyglot Coding: Proficient in Python, JavaScript, C++, Rust, and other major languages.
Base Model: Built on the powerful Qwen3-8B architecture.
Efficient: 8B size allows for local inference on consumer hardware (12GB+ VRAM recommended for FP16, less for quantized).

🧩 Merged Models

The following models were merged using equal weights to create uCoder-8b-base:

Model Name	Primary Contribution
Qwen3 8B GPT 5.2 High Reasoning Distill	Advanced logic & multi-step reasoning
Qwen3 8B Claude 4.5 Opus High Reasoning Distill	Safe code generation & detailed explanations
Qwen3 8B Gemini 3 Pro Preview Distill	Long-context handling & creative solutions
Qwen3 8B DeepSeek v3.2 Speciale Distill	Mathematical problem solving & optimization
Qwen3 8B GPT 5 Codex Distill	Syntax accuracy & API implementation

Limitations

Base Model Nature: This is a base model (merge), not fully instruction-tuned for chat. While it can handle chat formats, it performs best when fine-tuned or given specific few-shot examples.
Coding Focus: While capable of general reasoning, its domain expertise is heavily skewed towards programming and technical tasks.

License

This model is released under the Apache 2.0 license.

Downloads last month: 46

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for uaytug/uCoder-8b-base-GGUF

Base model

uaytug/uCoder-8b-base

Quantized

(6)

this model

Dataset used to train uaytug/uCoder-8b-base-GGUF

Collection including uaytug/uCoder-8b-base-GGUF

uCoder 8B

Collection

The collection of uCoder 8B Coding Focused LLM model that based on Qwen3-8b model • 6 items • Updated Jan 5