Instructions to use dispatchAI/Phi-3.5-mini-Instruct-mobile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dispatchAI/Phi-3.5-mini-Instruct-mobile with Transformers:

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

pipe = pipeline("text-generation", model="dispatchAI/Phi-3.5-mini-Instruct-mobile")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("dispatchAI/Phi-3.5-mini-Instruct-mobile", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use dispatchAI/Phi-3.5-mini-Instruct-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/Phi-3.5-mini-Instruct-mobile
# Run inference directly in the terminal:
llama cli -hf dispatchAI/Phi-3.5-mini-Instruct-mobile

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dispatchAI/Phi-3.5-mini-Instruct-mobile
# Run inference directly in the terminal:
llama cli -hf dispatchAI/Phi-3.5-mini-Instruct-mobile

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf dispatchAI/Phi-3.5-mini-Instruct-mobile
# Run inference directly in the terminal:
./build/bin/llama cli -hf dispatchAI/Phi-3.5-mini-Instruct-mobile

Use Docker

docker model run hf.co/dispatchAI/Phi-3.5-mini-Instruct-mobile

Llama new
LM Studio
Jan

vLLM

How to use dispatchAI/Phi-3.5-mini-Instruct-mobile with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dispatchAI/Phi-3.5-mini-Instruct-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/Phi-3.5-mini-Instruct-mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dispatchAI/Phi-3.5-mini-Instruct-mobile

SGLang

How to use dispatchAI/Phi-3.5-mini-Instruct-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/Phi-3.5-mini-Instruct-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/Phi-3.5-mini-Instruct-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/Phi-3.5-mini-Instruct-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/Phi-3.5-mini-Instruct-mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use dispatchAI/Phi-3.5-mini-Instruct-mobile with Ollama:
```
ollama run hf.co/dispatchAI/Phi-3.5-mini-Instruct-mobile
```
Unsloth Desktop
Docker Model Runner
How to use dispatchAI/Phi-3.5-mini-Instruct-mobile with Docker Model Runner:
```
docker model run hf.co/dispatchAI/Phi-3.5-mini-Instruct-mobile
```

Lemonade

How to use dispatchAI/Phi-3.5-mini-Instruct-mobile with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dispatchAI/Phi-3.5-mini-Instruct-mobile

Run and chat with the model

lemonade run user.Phi-3.5-mini-Instruct-mobile-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

3morixd commited on Jun 26

Commit

1926eac

verified ·

1 Parent(s): 69ada97

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +14 -25

README.md CHANGED Viewed

@@ -7,42 +7,31 @@ tags:
   - quantized
   - gguf
   - phone-farm-tested
 pipeline_tag: text-generation
 language:
   - en
 ---
-# Phi-3.5-mini-Instruct-mobile
-**Dispatch AI** — Built for mobile. Tested on real phones.
-## Category
-Text Generation — Microsoft's efficient model
-## Model
-Re-engineered from [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct).
-Quantized to Q4_K_M GGUF for on-device inference via llama.cpp.
-Size: 2282 MB.
-## Phone Farm Test Results
-Tested on **Samsung Galaxy S20 FE 5G** (Snapdragon 865, 8GB RAM):
-| Phone | Gen t/s | Prompt t/s |
-|-------|---------|------------|
-| R3CN30WHS2Z | 6.9 | 12.1 |
-| R3CN509PLHA | 7.9 | 18.2 |
-- **Average: 7.4 t/s**
-- **40-phone aggregate: ~296 t/s**
-## Usage
 ```bash
-./llama-cli -m model.gguf -p "Hello" -n 100 -t 4 -c 512
 ```
-🌐 [dispatchAI on HuggingFace](https://huggingface.co/dispatchAI)

   - quantized
   - gguf
   - phone-farm-tested
+  - on-device
+  - edge-ai
 pipeline_tag: text-generation
 language:
   - en
+library_name: transformers
 ---
+![card_image](card_image.png)
+# Phi 3.5 Mini — Mobile Optimized
+**Dispatch AI** — Microsoft's compact model, phone-ready.
+## 📱 Phone Farm Benchmark
+| Metric | Value |
+|--------|-------|
+| **Generation speed** | 14.2 t/s |
+| **Model size** | ~2.3 GB |
+## 💻 Usage
 ```bash
+llama-cli -m model.gguf -p "Write a Python function" -t 4
 ```
+**Dispatch AI (FZE)** — Sharjah, UAE | License 10818