Instructions to use RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-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 RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-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 RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-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 RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-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 RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf:Q4_K_M

Run and chat with the model

lemonade run user.LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

LLaMA-3-8B-SmoothQuant-4bit-4bit - GGUF

Model creator: https://huggingface.co/LLMQ/
Original model: https://huggingface.co/LLMQ/LLaMA-3-8B-SmoothQuant-4bit-4bit/

Name	Quant method	Size
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q2_K.gguf	Q2_K	2.96GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.IQ3_XS.gguf	IQ3_XS	3.28GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.IQ3_S.gguf	IQ3_S	3.43GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q3_K_S.gguf	Q3_K_S	3.41GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.IQ3_M.gguf	IQ3_M	3.52GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q3_K.gguf	Q3_K	3.74GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q3_K_M.gguf	Q3_K_M	3.74GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q3_K_L.gguf	Q3_K_L	4.03GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.IQ4_XS.gguf	IQ4_XS	4.18GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q4_0.gguf	Q4_0	4.34GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.IQ4_NL.gguf	IQ4_NL	4.38GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q4_K_S.gguf	Q4_K_S	4.37GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q4_K.gguf	Q4_K	4.58GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q4_K_M.gguf	Q4_K_M	4.58GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q4_1.gguf	Q4_1	4.78GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q5_0.gguf	Q5_0	5.21GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q5_K_S.gguf	Q5_K_S	5.21GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q5_K.gguf	Q5_K	5.34GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q5_K_M.gguf	Q5_K_M	5.34GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q5_1.gguf	Q5_1	5.65GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q6_K.gguf	Q6_K	6.14GB
LLaMA-3-8B-SmoothQuant-4bit-4bit.Q8_0.gguf	Q8_0	7.95GB

Original model description: Entry not found

Downloads last month: 565

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support