Instructions to use ykarout/llama3-deepseek_Q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ykarout/llama3-deepseek_Q8 with Transformers:

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

pipe = pipeline("text-generation", model="ykarout/llama3-deepseek_Q8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ykarout/llama3-deepseek_Q8", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ykarout/llama3-deepseek_Q8 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 ykarout/llama3-deepseek_Q8
# Run inference directly in the terminal:
llama cli -hf ykarout/llama3-deepseek_Q8

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ykarout/llama3-deepseek_Q8
# Run inference directly in the terminal:
llama cli -hf ykarout/llama3-deepseek_Q8

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 ykarout/llama3-deepseek_Q8
# Run inference directly in the terminal:
./llama-cli -hf ykarout/llama3-deepseek_Q8

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 ykarout/llama3-deepseek_Q8
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ykarout/llama3-deepseek_Q8

Use Docker

docker model run hf.co/ykarout/llama3-deepseek_Q8

LM Studio
Jan

vLLM

How to use ykarout/llama3-deepseek_Q8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ykarout/llama3-deepseek_Q8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ykarout/llama3-deepseek_Q8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ykarout/llama3-deepseek_Q8

SGLang

How to use ykarout/llama3-deepseek_Q8 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 "ykarout/llama3-deepseek_Q8" \
    --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": "ykarout/llama3-deepseek_Q8",
		"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 "ykarout/llama3-deepseek_Q8" \
        --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": "ykarout/llama3-deepseek_Q8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ykarout/llama3-deepseek_Q8 with Ollama:
```
ollama run hf.co/ykarout/llama3-deepseek_Q8
```
Unsloth Desktop

How to use ykarout/llama3-deepseek_Q8 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ykarout/llama3-deepseek_Q8

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ykarout/llama3-deepseek_Q8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ykarout/llama3-deepseek_Q8 with Docker Model Runner:
```
docker model run hf.co/ykarout/llama3-deepseek_Q8
```

Lemonade

How to use ykarout/llama3-deepseek_Q8 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ykarout/llama3-deepseek_Q8

Run and chat with the model

lemonade run user.llama3-deepseek_Q8-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use ykarout/llama3-deepseek_Q8 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ykarout/llama3-deepseek_Q8

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 ykarout/llama3-deepseek_Q8

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ykarout/llama3-deepseek_Q8 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ykarout/llama3-deepseek_Q8

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 "ykarout/llama3-deepseek_Q8" \
  --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"

Llama3-ThinkQ8

A fine-tuned version of Llama 3 that shows explicit thinking using <think> and <answer> tags. This model is quantized to 8-bit (Q8) for efficient inference.

Model Details

Base Model: Llama 3
Quantization: 8-bit (Q8)
Special Feature: Explicit thinking process with tags

How to Use with Ollama

1. Install Ollama

If you haven't already installed Ollama, follow the instructions at ollama.ai.

2. Download the model file

Download the GGUF file from this repository.

3. Create the Ollama model

Create a file named Modelfile with this content:

FROM llama3-thinkQ8.gguf
# Model parameters
PARAMETER temperature 0.8
PARAMETER top_p 0.9
# System prompt
SYSTEM """You are a helpful assistant. You will check the user request and you will think and generate brainstorming and self-thoughts in your mind and respond only in the following format:
<think> {your thoughts here} </think>
<answer> {your final answer here} </answer>. Use the tags once and place all your output inside them ONLY"""

Then run:

ollama create llama3-think -f Modelfile

4. Run the model

ollama run llama3-think

Example Prompts

Try these examples:

Using each number in this tensor ONLY once (5, 8, 3) and any arithmetic operation like add, subtract, multiply, divide, create an equation that equals 19.

Explain the concept of quantum entanglement to a high school student.

Downloads last month: 1

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for ykarout/llama3-deepseek_Q8

Base model

microsoft/phi-4

Quantized

unsloth/phi-4-unsloth-bnb-4bit

Quantized

(87)

this model

ykarout
/

llama3-deepseek_Q8

Llama3-ThinkQ8

Model Details

How to Use with Ollama

1. Install Ollama

2. Download the model file

3. Create the Ollama model

4. Run the model

Example Prompts

Model tree for ykarout/llama3-deepseek_Q8

Dataset used to train ykarout/llama3-deepseek_Q8