Instructions to use dispatchAI/Gemma-2-2B-IT-mobile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dispatchAI/Gemma-2-2B-IT-mobile with Transformers:

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

pipe = pipeline("text-generation", model="dispatchAI/Gemma-2-2B-IT-mobile", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("dispatchAI/Gemma-2-2B-IT-mobile", dtype="auto", device_map="auto")

llama-cpp-python

How to use dispatchAI/Gemma-2-2B-IT-mobile with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dispatchAI/Gemma-2-2B-IT-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/Gemma-2-2B-IT-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/Gemma-2-2B-IT-mobile
# Run inference directly in the terminal:
llama cli -hf dispatchAI/Gemma-2-2B-IT-mobile

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dispatchAI/Gemma-2-2B-IT-mobile
# Run inference directly in the terminal:
llama cli -hf dispatchAI/Gemma-2-2B-IT-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/Gemma-2-2B-IT-mobile
# Run inference directly in the terminal:
./llama-cli -hf dispatchAI/Gemma-2-2B-IT-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/Gemma-2-2B-IT-mobile
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dispatchAI/Gemma-2-2B-IT-mobile

Use Docker

docker model run hf.co/dispatchAI/Gemma-2-2B-IT-mobile

LM Studio
Jan

vLLM

How to use dispatchAI/Gemma-2-2B-IT-mobile with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dispatchAI/Gemma-2-2B-IT-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/Gemma-2-2B-IT-mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dispatchAI/Gemma-2-2B-IT-mobile

SGLang

How to use dispatchAI/Gemma-2-2B-IT-mobile 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 "dispatchAI/Gemma-2-2B-IT-mobile" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dispatchAI/Gemma-2-2B-IT-mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "dispatchAI/Gemma-2-2B-IT-mobile" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dispatchAI/Gemma-2-2B-IT-mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use dispatchAI/Gemma-2-2B-IT-mobile with Ollama:
```
ollama run hf.co/dispatchAI/Gemma-2-2B-IT-mobile
```

Unsloth Studio

How to use dispatchAI/Gemma-2-2B-IT-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/Gemma-2-2B-IT-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/Gemma-2-2B-IT-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/Gemma-2-2B-IT-mobile to start chatting

Atomic Chat new
Docker Model Runner
How to use dispatchAI/Gemma-2-2B-IT-mobile with Docker Model Runner:
```
docker model run hf.co/dispatchAI/Gemma-2-2B-IT-mobile
```

Lemonade

How to use dispatchAI/Gemma-2-2B-IT-mobile with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dispatchAI/Gemma-2-2B-IT-mobile

Run and chat with the model

lemonade run user.Gemma-2-2B-IT-mobile-{{QUANT_TAG}}

List all available models

lemonade list

3morixd commited on 24 days ago

Commit

a1a2f36

verified ·

1 Parent(s): 6c80b8c

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +45 -22

README.md CHANGED Viewed

@@ -1,38 +1,61 @@
 ---
-license: apache-2.0
-base_model: google/gemma-2-2b-it
 tags:
-  - dispatch-ai
   - mobile
   - quantized
   - gguf
-  - phone-farm-tested
-  - on-device
-  - edge-ai
 pipeline_tag: text-generation
-language:
-  - en
-library_name: transformers
 ---
-![card_image](card_image.png)
-# Gemma 2 2B IT — Mobile Optimized
-**Dispatch AI** — Google's Gemma, re-engineered for phones.
-## 📱 Phone Farm Benchmark
-| Metric | Value |
-|--------|-------|
-| **Generation speed** | 13.8 t/s |
-| **Model size** | ~1.6 GB |
-| **Load time** | 2.5s |
-## 💻 Usage
-```bash
-llama-cli -m model.gguf -p "What is the meaning of life?" -t 4
 ```
-**Dispatch AI (FZE)** — Sharjah, UAE | License 10818

 ---
+license: gemma
+language:
+  - en
+library_name: transformers
 tags:
   - mobile
+  - on-device
   - quantized
   - gguf
+  - dispatchai
 pipeline_tag: text-generation
 ---
+# Gemma-2-2B-IT-mobile
+✅ **WORKS** — Verified June 2026.
+## Verification Results
+| Prompt | Response | Correct? |
+|--------|----------|----------|
+| What is the capital of France? | "The capital of France is **Paris**." | ✅ |
+| What is 2+2? Just the number. | "4" | ✅ |
+**Chat format**: `gemma`
+## Model Details
+| Attribute | Value |
+|-----------|-------|
+| **Base Model** | google/gemma-2-2b-it |
+| **File Size** | 1629 MB |
+| **Format** | GGUF |
+| **Chat Format** | gemma |
+| **CPU Speed** | 8.2 tokens/sec |
+| **License** | gemma |
+## Usage
+```python
+from llama_cpp import Llama
+llm = Llama(model_path="model.gguf", chat_format="gemma", n_ctx=512, n_threads=4)
+response = llm.create_chat_completion(
+    messages=[{"role": "user", "content": "What is the capital of France?"}],
+    max_tokens=50,
+)
+print(response["choices"][0]["message"]["content"])
 ```
+### dispatchAI SDK
+```python
+from dispatchai import load_model
+model = load_model("Gemma-2-2B-IT-mobile", backend="gguf")
+print(model.chat("Hello!"))
+```
+## About dispatchAI
+[dispatchAI](https://huggingface.co/dispatchAI) — Small. Mobile. Free. UAE-built.