Instructions to use FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-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 FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-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 FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-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 serve -hf FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-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 FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-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 FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF

This is a Q4_K_M GGUF quantization of tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5, converted using llama.cpp.

Usage with Ollama

ollama run hf.co/FalconSuzuki/Llama-3.1-Swallow-8B-Instruct-v0.5-Q4_K_M-GGUF:Q4_K_M

Usage with llama.cpp

llama-cli -m llama-3.1-swallow-8b-instruct-v0.5-Q4_K_M.gguf -cnv -c 4096

Note: the model's native context length is 131072, but a smaller context size (e.g. 4096) is recommended for typical local use to avoid excessive memory usage.