Instructions to use NikolayKozloff/granite-8b-code-base-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NikolayKozloff/granite-8b-code-base-Q8_0-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="NikolayKozloff/granite-8b-code-base-Q8_0-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NikolayKozloff/granite-8b-code-base-Q8_0-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NikolayKozloff/granite-8b-code-base-Q8_0-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 NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0

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 NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0

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 NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use NikolayKozloff/granite-8b-code-base-Q8_0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NikolayKozloff/granite-8b-code-base-Q8_0-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NikolayKozloff/granite-8b-code-base-Q8_0-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0

SGLang

How to use NikolayKozloff/granite-8b-code-base-Q8_0-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 "NikolayKozloff/granite-8b-code-base-Q8_0-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": "NikolayKozloff/granite-8b-code-base-Q8_0-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 "NikolayKozloff/granite-8b-code-base-Q8_0-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": "NikolayKozloff/granite-8b-code-base-Q8_0-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use NikolayKozloff/granite-8b-code-base-Q8_0-GGUF with Ollama:
```
ollama run hf.co/NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0
```

Unsloth Studio

How to use NikolayKozloff/granite-8b-code-base-Q8_0-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 NikolayKozloff/granite-8b-code-base-Q8_0-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 NikolayKozloff/granite-8b-code-base-Q8_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NikolayKozloff/granite-8b-code-base-Q8_0-GGUF to start chatting

Docker Model Runner
How to use NikolayKozloff/granite-8b-code-base-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0
```

Lemonade

How to use NikolayKozloff/granite-8b-code-base-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NikolayKozloff/granite-8b-code-base-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.granite-8b-code-base-Q8_0-GGUF-Q8_0

List all available models

lemonade list

Atomic Chat

NikolayKozloff/granite-8b-code-base-Q8_0-GGUF

This model was converted to GGUF format from ibm-granite/granite-8b-code-base using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew.

brew install ggerganov/ggerganov/llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo NikolayKozloff/granite-8b-code-base-Q8_0-GGUF --model granite-8b-code-base.Q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo NikolayKozloff/granite-8b-code-base-Q8_0-GGUF --model granite-8b-code-base.Q8_0.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m granite-8b-code-base.Q8_0.gguf -n 128

Downloads last month: 39

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

8-bit

Datasets used to train NikolayKozloff/granite-8b-code-base-Q8_0-GGUF

Evaluation results

pass@1 on MBPP
self-reported

42.200
pass@1 on MBPP+
self-reported

49.600
pass@1 on HumanEvalSynthesis(Python)
self-reported

43.900
pass@1 on HumanEvalSynthesis(Python)
self-reported

52.400
pass@1 on HumanEvalSynthesis(Python)
self-reported

56.100
pass@1 on HumanEvalSynthesis(Python)
self-reported

31.700
pass@1 on HumanEvalSynthesis(Python)
self-reported

43.900
pass@1 on HumanEvalSynthesis(Python)
self-reported

32.900