Instructions to use marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-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 marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-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 marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16
# Run inference directly in the terminal:
llama cli -hf marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16
# Run inference directly in the terminal:
llama cli -hf marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16

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 marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16
# Run inference directly in the terminal:
./llama-cli -hf marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16

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 marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16

Use Docker

docker model run hf.co/marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16

LM Studio
Jan
Ollama
How to use marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf with Ollama:
```
ollama run hf.co/marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16
```
Unsloth Desktop
Docker Model Runner
How to use marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf with Docker Model Runner:
```
docker model run hf.co/marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16
```

Lemonade

How to use marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull marcelone/Llama-3.1-Swallow-8B-Instruct-v0.5-gguf:BF16

Run and chat with the model

lemonade run user.Llama-3.1-Swallow-8B-Instruct-v0.5-gguf-BF16

List all available models

lemonade list

Atomic Chat

marcelone commited on Jul 27, 2025

Commit

08a0944

verified ·

1 Parent(s): a974098

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -0

README.md CHANGED Viewed

@@ -7,6 +7,12 @@ base_model:
 - tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5
 base_model_relation: quantized
 ---
 # Swallow-8B-it-v05-gguf-q8_0-mixed-v1
 * **Quantization Type**: Mixed Precision (`bf16`, `q4_K`, `q5_K`, `q6_K`, `q8_0`)
 * **Bits Per Weight (BPW)**: `8.01`

 - tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5
 base_model_relation: quantized
 ---
+# Swallow-8B-it-v05-gguf-q6_k-mixed-v1
+* **Quantization Type**: Mixed Precision (`q5_K`, `q6_K`, `q8_0`)
+* **Bits Per Weight (BPW)**: `7.13`
+# Swallow-8B-it-v05-gguf-q6_k-mixed-v2
+* **Quantization Type**: Mixed Precision (`q6_K`, `q8_0`)
+* **Bits Per Weight (BPW)**: `7.50`
 # Swallow-8B-it-v05-gguf-q8_0-mixed-v1
 * **Quantization Type**: Mixed Precision (`bf16`, `q4_K`, `q5_K`, `q6_K`, `q8_0`)
 * **Bits Per Weight (BPW)**: `8.01`