---
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
tags:
  - dispatch-ai
  - mobile
  - quantized
  - gguf
  - phone-farm-tested
pipeline_tag: text-generation
language:
  - en
---

# SmolLM2-1.7B-Instruct-mobile

**Dispatch AI** — Built for mobile. Tested on real phones.

## Category

Text Generation — HuggingFace's small but capable model

## Model

Re-engineered from [HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct).
Quantized to Q4_K_M GGUF for on-device inference via llama.cpp.
Size: 1007 MB.

## Phone Farm Test Results

Tested on **Samsung Galaxy S20 FE 5G** (Snapdragon 865, 8GB RAM):

| Phone | Gen t/s | Prompt t/s |
|-------|---------|------------|
| R3CN30WHS2Z | 15.2 | 46.9 |
| R3CN509PLHA | 15.7 | 47.8 |

- **Average: 15.4 t/s**
- **40-phone aggregate: ~618 t/s**


## Usage

```bash
./llama-cli -m model.gguf -p "Hello" -n 100 -t 4 -c 512
```

🌐 [dispatchAI on HuggingFace](https://huggingface.co/dispatchAI)