Instructions to use vhab10/llama_3.1_8b_Q4_K_M-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vhab10/llama_3.1_8b_Q4_K_M-gguf with Transformers:

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

pipe = pipeline("text-generation", model="vhab10/llama_3.1_8b_Q4_K_M-gguf")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vhab10/llama_3.1_8b_Q4_K_M-gguf", dtype="auto")

llama-cpp-python

How to use vhab10/llama_3.1_8b_Q4_K_M-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vhab10/llama_3.1_8b_Q4_K_M-gguf",
	filename="llama_3.1_8b_Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use vhab10/llama_3.1_8b_Q4_K_M-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vhab10/llama_3.1_8b_Q4_K_M-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vhab10/llama_3.1_8b_Q4_K_M-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 vhab10/llama_3.1_8b_Q4_K_M-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vhab10/llama_3.1_8b_Q4_K_M-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 vhab10/llama_3.1_8b_Q4_K_M-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vhab10/llama_3.1_8b_Q4_K_M-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 vhab10/llama_3.1_8b_Q4_K_M-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vhab10/llama_3.1_8b_Q4_K_M-gguf:Q4_K_M

Use Docker

docker model run hf.co/vhab10/llama_3.1_8b_Q4_K_M-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use vhab10/llama_3.1_8b_Q4_K_M-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vhab10/llama_3.1_8b_Q4_K_M-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vhab10/llama_3.1_8b_Q4_K_M-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vhab10/llama_3.1_8b_Q4_K_M-gguf:Q4_K_M

SGLang

How to use vhab10/llama_3.1_8b_Q4_K_M-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 "vhab10/llama_3.1_8b_Q4_K_M-gguf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vhab10/llama_3.1_8b_Q4_K_M-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "vhab10/llama_3.1_8b_Q4_K_M-gguf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vhab10/llama_3.1_8b_Q4_K_M-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use vhab10/llama_3.1_8b_Q4_K_M-gguf with Ollama:
```
ollama run hf.co/vhab10/llama_3.1_8b_Q4_K_M-gguf:Q4_K_M
```

Unsloth Studio

How to use vhab10/llama_3.1_8b_Q4_K_M-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 vhab10/llama_3.1_8b_Q4_K_M-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 vhab10/llama_3.1_8b_Q4_K_M-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vhab10/llama_3.1_8b_Q4_K_M-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use vhab10/llama_3.1_8b_Q4_K_M-gguf with Docker Model Runner:
```
docker model run hf.co/vhab10/llama_3.1_8b_Q4_K_M-gguf:Q4_K_M
```

Lemonade

How to use vhab10/llama_3.1_8b_Q4_K_M-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vhab10/llama_3.1_8b_Q4_K_M-gguf:Q4_K_M

Run and chat with the model

lemonade run user.llama_3.1_8b_Q4_K_M-gguf-Q4_K_M

List all available models

lemonade list

Llama 3.1 8B Q4_K_M GGUF Model

Overview

This is the quantized version of the Llama 3.1 8B model in Q4_K_M format, optimized for efficient inference on both CPU and GPU. The model was quantized using the llama.cpp library, allowing users to run it in resource-constrained environments . This quantization reduces the model's memory footprint while maintaining strong language generation capabilities.

The model was originally trained by Meta AI and has been adapted to the GGUF format for compatibility with llama.cpp.

Model Details

Base Model: meta-llama/Llama-3.1-8B
Quantization Type: Q4_K_M (4-bit quantization with memory optimization)
Model Size: 8B parameters
Format: GGUF (used for efficient loading in llama.cpp)
Intended Use: Text generation, inference on CPUs/GPUs with reduced memory constraints

Intended Use

The model is intended for text generation tasks and is optimized for efficient inference on both CPUs and GPUs, making it suitable for use in resource-constrained environments.

License

This model is licensed under the Apache 2.0 License.

Downloads last month: 10

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for vhab10/llama_3.1_8b_Q4_K_M-gguf

Base model

meta-llama/Llama-3.1-8B

Quantized

(325)

this model