Instructions to use madhuHuggingface/functiongemma-vpc-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 madhuHuggingface/functiongemma-vpc-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 madhuHuggingface/functiongemma-vpc-gguf:F16
# Run inference directly in the terminal:
llama cli -hf madhuHuggingface/functiongemma-vpc-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf madhuHuggingface/functiongemma-vpc-gguf:F16
# Run inference directly in the terminal:
llama cli -hf madhuHuggingface/functiongemma-vpc-gguf:F16

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 madhuHuggingface/functiongemma-vpc-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf madhuHuggingface/functiongemma-vpc-gguf:F16

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 madhuHuggingface/functiongemma-vpc-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf madhuHuggingface/functiongemma-vpc-gguf:F16

Use Docker

docker model run hf.co/madhuHuggingface/functiongemma-vpc-gguf:F16

LM Studio
Jan
Ollama
How to use madhuHuggingface/functiongemma-vpc-gguf with Ollama:
```
ollama run hf.co/madhuHuggingface/functiongemma-vpc-gguf:F16
```

Unsloth Studio

How to use madhuHuggingface/functiongemma-vpc-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 madhuHuggingface/functiongemma-vpc-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 madhuHuggingface/functiongemma-vpc-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for madhuHuggingface/functiongemma-vpc-gguf to start chatting

How to use madhuHuggingface/functiongemma-vpc-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf madhuHuggingface/functiongemma-vpc-gguf:F16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "madhuHuggingface/functiongemma-vpc-gguf:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use madhuHuggingface/functiongemma-vpc-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf madhuHuggingface/functiongemma-vpc-gguf:F16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "madhuHuggingface/functiongemma-vpc-gguf:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use madhuHuggingface/functiongemma-vpc-gguf with Docker Model Runner:
```
docker model run hf.co/madhuHuggingface/functiongemma-vpc-gguf:F16
```

Lemonade

How to use madhuHuggingface/functiongemma-vpc-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull madhuHuggingface/functiongemma-vpc-gguf:F16

Run and chat with the model

lemonade run user.functiongemma-vpc-gguf-F16

List all available models

lemonade list

Hermes Agent

How to use madhuHuggingface/functiongemma-vpc-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf madhuHuggingface/functiongemma-vpc-gguf:F16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default madhuHuggingface/functiongemma-vpc-gguf:F16

Run Hermes

hermes

Atomic Chat

madhuHuggingface commited on May 23

Commit

4ed619a

verified ·

1 Parent(s): 2e62a4f

Upload folder using huggingface_hub

Browse files

Files changed (5) hide show

.gitattributes +1 -0
README.md +5 -14
config.json +2 -2
functiongemma-vpc-q4_k_m.gguf +3 -0
generation_config.json +14 -0

.gitattributes CHANGED Viewed

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 functiongemma-vpc-f16.gguf filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 functiongemma-vpc-f16.gguf filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+functiongemma-vpc-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -1,26 +1,17 @@
 ---
 license: apache-2.0
 base_model: google/functiongemma-270m-it
-tags:
-  - function-calling
-  - vpc
-  - gguf
-  - q4_k_m
 ---
 # FunctionGemma-270M VPC — GGUF Q4_K_M
-Fine-tuned for VPC & Routing tool-calling. Quantized to Q4_K_M GGUF for CPU inference.
-## Install
-```bash
-pip install llama-cpp-python transformers sentencepiece
-```
 ## Quick use
 ```python
 from huggingface_hub import hf_hub_download
-gguf_path = hf_hub_download(repo_id='madhuHuggingface/functiongemma-vpc-gguf', filename='functiongemma-vpc-q4_k_m.gguf')
 ```
-See the companion `vpc_local_test.py` for the full 30-test evaluation.

 ---
 license: apache-2.0
 base_model: google/functiongemma-270m-it
+tags: [function-calling, vpc, gguf, q4_k_m]
 ---
 # FunctionGemma-270M VPC — GGUF Q4_K_M
+Fine-tuned for VPC & Routing tool-calling. Quantized to Q4_K_M GGUF for CPU inference (~253 MB).
 ## Quick use
 ```python
 from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
+gguf = hf_hub_download(repo_id="madhuHuggingface/functiongemma-vpc-gguf", filename="functiongemma-vpc-q4_k_m.gguf")
+llm  = Llama(model_path=gguf, n_ctx=4096, n_gpu_layers=0)
 ```

config.json CHANGED Viewed

@@ -36,7 +36,7 @@
         "full_attention"
     ],
     "max_position_embeddings": 32768,
-    "model_name": "unsloth/functiongemma-270m-it",
     "model_type": "gemma3_text",
     "num_attention_heads": 4,
     "num_hidden_layers": 18,
@@ -57,7 +57,7 @@
     "sliding_window": 512,
     "tie_word_embeddings": true,
     "unsloth_fixed": true,
-    "unsloth_version": "2026.5.2",
     "use_bidirectional_attention": false,
     "use_cache": true,
     "vocab_size": 262144

         "full_attention"
     ],
     "max_position_embeddings": 32768,
+    "model_name": "unsloth/functiongemma-270m-it-unsloth-bnb-4bit",
     "model_type": "gemma3_text",
     "num_attention_heads": 4,
     "num_hidden_layers": 18,
     "sliding_window": 512,
     "tie_word_embeddings": true,
     "unsloth_fixed": true,
+    "unsloth_version": "2026.5.6",
     "use_bidirectional_attention": false,
     "use_cache": true,
     "vocab_size": 262144

functiongemma-vpc-q4_k_m.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1fa2e0b79ed54ebbacf7ffbc17c050af115eea29ff38a96ec7aabb00d1eda3
+size 253127040

generation_config.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    50,
+    106
+  ],
+  "max_length": 32768,
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.0"
+}