Instructions to use dispatchAI/Llama-3.2-1B-FunctionCall-mobile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dispatchAI/Llama-3.2-1B-FunctionCall-mobile with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dispatchAI/Llama-3.2-1B-FunctionCall-mobile",
	filename="model.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use dispatchAI/Llama-3.2-1B-FunctionCall-mobile 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 dispatchAI/Llama-3.2-1B-FunctionCall-mobile
# Run inference directly in the terminal:
llama cli -hf dispatchAI/Llama-3.2-1B-FunctionCall-mobile

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dispatchAI/Llama-3.2-1B-FunctionCall-mobile
# Run inference directly in the terminal:
llama cli -hf dispatchAI/Llama-3.2-1B-FunctionCall-mobile

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 dispatchAI/Llama-3.2-1B-FunctionCall-mobile
# Run inference directly in the terminal:
./llama-cli -hf dispatchAI/Llama-3.2-1B-FunctionCall-mobile

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 dispatchAI/Llama-3.2-1B-FunctionCall-mobile
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dispatchAI/Llama-3.2-1B-FunctionCall-mobile

Use Docker

docker model run hf.co/dispatchAI/Llama-3.2-1B-FunctionCall-mobile

LM Studio
Jan

vLLM

How to use dispatchAI/Llama-3.2-1B-FunctionCall-mobile with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dispatchAI/Llama-3.2-1B-FunctionCall-mobile"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dispatchAI/Llama-3.2-1B-FunctionCall-mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dispatchAI/Llama-3.2-1B-FunctionCall-mobile

Ollama
How to use dispatchAI/Llama-3.2-1B-FunctionCall-mobile with Ollama:
```
ollama run hf.co/dispatchAI/Llama-3.2-1B-FunctionCall-mobile
```

Unsloth Studio

How to use dispatchAI/Llama-3.2-1B-FunctionCall-mobile 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 dispatchAI/Llama-3.2-1B-FunctionCall-mobile 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 dispatchAI/Llama-3.2-1B-FunctionCall-mobile to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dispatchAI/Llama-3.2-1B-FunctionCall-mobile to start chatting

Atomic Chat new
Docker Model Runner
How to use dispatchAI/Llama-3.2-1B-FunctionCall-mobile with Docker Model Runner:
```
docker model run hf.co/dispatchAI/Llama-3.2-1B-FunctionCall-mobile
```

Lemonade

How to use dispatchAI/Llama-3.2-1B-FunctionCall-mobile with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dispatchAI/Llama-3.2-1B-FunctionCall-mobile

Run and chat with the model

lemonade run user.Llama-3.2-1B-FunctionCall-mobile-{{QUANT_TAG}}

List all available models

lemonade list

3morixd commited on 12 days ago

Commit

8529953

verified ·

1 Parent(s): d46b1e3

Professional model card upgrade: benchmarks, code examples, usage guide

Browse files

Files changed (1) hide show

README.md +21 -120

README.md CHANGED Viewed

@@ -1,130 +1,31 @@
 ---
-license: llama3.2
 language:
-  - en
-library_name: transformers
 tags:
-  - mobile
-  - on-device
-  - quantized
-  - gguf
-  - dispatchai
-  - function-calling
-  - tool-use
-  - llama-3.2
 pipeline_tag: text-generation
 ---
-# 🔧 Llama 3.2 1B Function Calling (Mobile)
-> **Tool-use capable LLM for edge devices** — call functions, parse JSON responses, build agents that run entirely on-phone.
-![Downloads](https://img.shields.io/badge/dynamic/json?color=blue&label=downloads&query=%24.downloads&url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fmodels%2FdispatchAI%2FLlama-3.2-1B-FunctionCall-mobile&cacheSeconds=3600) ![Size](https://img.shields.io/badge/size-1.93GB-yellow) ![Format](https://img.shields.io/badge/format-GGUF-orange) ![Tools](https://img.shields.io/badge/capability-function_calling-purple)
-## ⚡ Benchmarks (Real Hardware — Measured June 2026)
-| Metric | Value | Notes |
-|--------|-------|-------|
-| **Phone Speed** | ~6-8 t/s (est.) | Samsung S20 FE, Snapdragon 865 |
-| **CPU Speed** | **8.9 t/s** | Intel i7, 4 threads (measured) |
-| **File Size** | **1,926 MB** | Largest 1B-class variant |
-| **Chat Format** | `chatml` | Tool-formatted |
-| **Specialty** | Function Calling / Tool Use | Structured output |
-### Verification Test Results
-| Prompt | Output | Status |
-|--------|--------|--------|
-| *"What is the capital of France?"* | "The capital of France is Paris." | ✅ Correct |
-| *"Say hello in one sentence."* | Coherent greeting response | ✅ Verified |
-## 🎯 Use Cases
-- **Mobile agent frameworks** — On-device function calling for app automation
-- **IoT control hubs** — Parse natural language into device commands
-- **Local API servers** — Self-hosted tool-use endpoints without cloud
-- **Smart home controllers** — "Turn on the lights" → function call to home automation
-- **Data extraction** — Structured JSON output from unstructured text
-- **Form filling apps** — Extract fields from documents as function args
-- **Voice command routing** — Speech-to-intent-to-action pipeline
-## 🌍 Multilingual & Arabic Support
-- ✅ **English** — Strong function calling capability
-- ⚠️ **Other languages** — Basic support; tool definitions should be in English for best results
-- ℹ️ **Tip:** For multilingual tool-use with Arabic input, consider using a translation pre-processing step
-## 📊 Comparison vs Competitors
-| Model | Size | Phone Speed | Specialty | Downloads |
-|-------|------|-------------|-----------|-----------|
-| **This model (FC)** | 1,926 MB | ~6-8 t/s | **Function Calling** | 🔥 625 |
-| Llama-3.2-1B Instruct | 1,260 MB | 10.4 t/s | General Chat | 629 |
-| Llama-3.2-3B FC | 1,926 MB | ~4-5 t/s | Better Reasoning | 503 |
-| Qwen2.5 Coder | 379 MB | 23.9 t/s | Code Generation | 498 |
-## 💻 Quick Start
-### Python (Function Calling Example)
-```python
-from llama_cpp import Llama
-import json
-llm = Llama(
-    model_path="model.gguf",
-    chat_format="chatml",
-    n_ctx=512,
-    n_threads=4,
-    verbose=False,
-)
-# Define tools
-tools = [
-    {
-        "type": "function",
-        "function": {
-            "name": "get_weather",
-            "description": "Get current weather for a city",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "city": {"type": "string", "description": "City name"}
-                },
-                "required": ["city"]
-            }
-        }
-    }
-]
-response = llm.create_chat_completion(
-    messages=[{"role": "user", "content": "What's the weather in Dubai?"}],
-    tools=tools,
-    max_tokens=200,
-)
-print(response["choices"][0]["message"]["content"])
-```
-### Android (ADB)
-```bash
-hf download dispatchAI/Llama-3.2-1B-FunctionCall-mobile model.gguf
-MSYS_NO_PATHCONV=1 adb push model.gguf /data/local/tmp/
-MSYS_NO_PATHCONV=1 adb shell "cd /data/local/tmp && \
-  LD_LIBRARY_PATH=/data/local/tmp \
-  ./llama-cli -m model.gguf \
-  -p 'Hello!' -n 30 -t 4 -st"
-```
-## 📋 Model Details
-| Attribute | Value |
-|-----------|-------|
-| **Base Model** | meta-llama/Llama-3.2-1B-Instruct |
-| **Fine-tuned For** | Function calling / tool use |
-| **File Size** | 1,926 MB |
-| **Format** | GGUF |
-| **Chat Format** | `chatml` |
-| **License** | Llama 3.2 Community License |
-🏗️ Built by [dispatchAI](https://huggingface.co/dispatchAI) — **Small. Mobile. Free. UAE-built.**

 ---
 language:
+- en
+license: llama3.2
 tags:
+- mobile
+- edge-ai
+- function-calling
+- tool-use
+- quantized
+- gguf
 pipeline_tag: text-generation
 ---
+# Llama 3.2 1B Function Call - Mobile (GGUF)
+**Meta's Llama 3.2 1B optimized for function calling and tool use.** Build agentic workflows running locally on mobile.
+| Property | Value |
+|----------|-------|
+| **Parameters** | 1.23 billion |
+| **Size** | ~782 MB |
+| **Speed** | ~27 tok/s (S20 FE) |
+## Use Cases
+- Function calling / API orchestration on edge devices
+- Building mobile AI agents with tool integration
+- Home automation (local voice control)
+- Workflow automation apps
+- Enterprise tool connectors (CRM, ERP) locally