Instructions to use dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile with Transformers:

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

pipe = pipeline("text-generation", model="dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use dispatchAI/SmolLM2-1.7B-Instruct-Q5-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/SmolLM2-1.7B-Instruct-Q5-mobile
# Run inference directly in the terminal:
llama cli -hf dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile
# Run inference directly in the terminal:
llama cli -hf dispatchAI/SmolLM2-1.7B-Instruct-Q5-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/SmolLM2-1.7B-Instruct-Q5-mobile
# Run inference directly in the terminal:
./build/bin/llama cli -hf dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile

Use Docker

docker model run hf.co/dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile

Llama new
LM Studio
Jan

vLLM

How to use dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dispatchAI/SmolLM2-1.7B-Instruct-Q5-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/SmolLM2-1.7B-Instruct-Q5-mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile

SGLang

How to use dispatchAI/SmolLM2-1.7B-Instruct-Q5-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/SmolLM2-1.7B-Instruct-Q5-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/SmolLM2-1.7B-Instruct-Q5-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/SmolLM2-1.7B-Instruct-Q5-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/SmolLM2-1.7B-Instruct-Q5-mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile with Ollama:
```
ollama run hf.co/dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile
```
Unsloth Desktop
Docker Model Runner
How to use dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile with Docker Model Runner:
```
docker model run hf.co/dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile
```

Lemonade

How to use dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dispatchAI/SmolLM2-1.7B-Instruct-Q5-mobile

Run and chat with the model

lemonade run user.SmolLM2-1.7B-Instruct-Q5-mobile-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

3morixd commited on Jun 26

Commit

fb458e2

verified ·

1 Parent(s): 6ce93cb

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +7 -10

README.md CHANGED Viewed

@@ -14,16 +14,15 @@ pipeline_tag: text-generation
 # SmolLM2-1.7B-Instruct-Q5-mobile
-⚠️ **PARTIAL** — Verified June 2026.
 ## Verification Results
 | Prompt | Response | Correct? |
 |--------|----------|----------|
-| What is the capital of France? | "What is the capital of France?" | ⚠️ |
-| What is 2+2? Just the number. | "2+2=4." | ✅ |
-**Chat format**: `llama-3`
 ## Model Details
@@ -32,8 +31,8 @@ pipeline_tag: text-generation
 | **Base Model** | HuggingFaceTB/SmolLM2-1.7B-Instruct |
 | **File Size** | 1169 MB |
 | **Format** | GGUF |
-| **Chat Format** | llama-3 |
-| **CPU Speed** | 10.6 tokens/sec |
 | **License** | apache-2.0 |
 ## Usage
@@ -41,7 +40,7 @@ pipeline_tag: text-generation
 ```python
 from llama_cpp import Llama
-llm = Llama(model_path="model.gguf", chat_format="llama-3", n_ctx=512, n_threads=4)
 response = llm.create_chat_completion(
     messages=[{"role": "user", "content": "What is the capital of France?"}],
     max_tokens=50,
@@ -56,6 +55,4 @@ model = load_model("SmolLM2-1.7B-Instruct-Q5-mobile", backend="gguf")
 print(model.chat("Hello!"))
 ```
-## About dispatchAI
-[dispatchAI](https://huggingface.co/dispatchAI) — Small. Mobile. Free. UAE-built.

 # SmolLM2-1.7B-Instruct-Q5-mobile
+✅ **WORKS** — Verified June 2026.
 ## Verification Results
 | Prompt | Response | Correct? |
 |--------|----------|----------|
+| What is the capital of France? | "The capital of France is Paris." | ✅ |
+| Say hello in one sentence. | "Hello, I'm here to help with any programming tasks you may n" | ✅ |
 ## Model Details
 | **Base Model** | HuggingFaceTB/SmolLM2-1.7B-Instruct |
 | **File Size** | 1169 MB |
 | **Format** | GGUF |
+| **Chat Format** | chatml |
+| **CPU Speed** | 10.8 tokens/sec |
 | **License** | apache-2.0 |
 ## Usage
 ```python
 from llama_cpp import Llama
+llm = Llama(model_path="model.gguf", chat_format="chatml", n_ctx=512, n_threads=4, verbose=False)
 response = llm.create_chat_completion(
     messages=[{"role": "user", "content": "What is the capital of France?"}],
     max_tokens=50,
 print(model.chat("Hello!"))
 ```
+🚀 [dispatchAI](https://huggingface.co/dispatchAI)