---
license: apache-2.0
language:
  - en
library_name: transformers
tags:
  - mobile
  - on-device
  - quantized
  - gguf
  - dispatchai
pipeline_tag: text-generation
---

# SmolLM2-135M-Instruct-mobile

✅ **Verified on real phone hardware** — Snapdragon 865, June 2026.

## Phone Benchmark (Samsung S20 FE, Snapdragon 865)

| Metric | Value |
|--------|-------|
| **Phone Speed** | **46.2 tokens/sec** |
| **CPU Speed** | 59.7 tokens/sec |
| **File Size** | 0 MB |
| **Chat Format** | llama-3 |
| **Test Output** | "Paris" ✅ (correct) |

## Usage

### Python (llama-cpp-python)
```python
from llama_cpp import Llama

llm = Llama(model_path="model.gguf", chat_format="llama-3", 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(response["choices"][0]["message"]["content"])
```

### dispatchAI SDK
```python
from dispatchai import load_model
model = load_model("SmolLM2-135M-Instruct-mobile", backend="gguf")
print(model.chat("What is the capital of France?"))
```

### On Android (via ADB)
```bash
hf download dispatchAI/SmolLM2-135M-Instruct-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** | HuggingFaceTB/SmolLM2-135M-Instruct |
| **File Size** | 0 MB |
| **Format** | GGUF |
| **Chat Format** | llama-3 |
| **License** | apache-2.0 |

## About dispatchAI

[dispatchAI](https://huggingface.co/dispatchAI) — Small. Mobile. Free. UAE-built.