Instructions to use tensorblock/granite-20b-functioncalling-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/granite-20b-functioncalling-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/granite-20b-functioncalling-GGUF",
	filename="granite-20b-functioncalling-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/granite-20b-functioncalling-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/granite-20b-functioncalling-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/granite-20b-functioncalling-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/granite-20b-functioncalling-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/granite-20b-functioncalling-GGUF:Q2_K

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 tensorblock/granite-20b-functioncalling-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/granite-20b-functioncalling-GGUF:Q2_K

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 tensorblock/granite-20b-functioncalling-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/granite-20b-functioncalling-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/granite-20b-functioncalling-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/granite-20b-functioncalling-GGUF with Ollama:
```
ollama run hf.co/tensorblock/granite-20b-functioncalling-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/granite-20b-functioncalling-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 tensorblock/granite-20b-functioncalling-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 tensorblock/granite-20b-functioncalling-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/granite-20b-functioncalling-GGUF to start chatting

Docker Model Runner
How to use tensorblock/granite-20b-functioncalling-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/granite-20b-functioncalling-GGUF:Q2_K
```

Lemonade

How to use tensorblock/granite-20b-functioncalling-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/granite-20b-functioncalling-GGUF:Q2_K

Run and chat with the model

lemonade run user.granite-20b-functioncalling-GGUF-Q2_K

List all available models

lemonade list

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6e0e8adc1620a40ba42c6066046ce8732c83e8e0c5d7a238d0441bd523583272
-size 11736504672

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f6e34f538fad5f5cd12e8c1eedf8dfc9d3c4300dd0b172eda04a3b34b1c47364
-size 8934594912

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f5c96318349c5866dd66931e1e48973a8aa42b6a078b42c65e04b4f7749127c3
-size 11552479584

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e52e7ce1ed801a6d61c50d6ccf85d595127b5d8f0e7ccfb746edbef08da26951
-size 12820207968

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:62a95243dd259e600824e5b89108628566ff4a35c4ae4e3db42e671443c380e9
-size 11665725792

tensorblock
/

granite-20b-functioncalling-GGUF

Keep Q2_K/Q3_K_M gguf only