Qwen 2.5 0.5B Instruct - Mobile INT4 (GGUF)
Alibaba's Qwen 2.5 0.5B Instruct, the smallest capable general-purpose model. Incredibly fast on phones.
| Property | Value |
|---|---|
| Base | Qwen/Qwen2.5-0.5B-Instruct |
| Parameters | 494 million |
| Quantization | INT4 GGUF |
| Size | ~398 MB |
| License | Apache 2.0 |
Performance
- ~45 tok/s on Samsung S20 FE CPU (fastest in our collection!)
- ~0.7 GB memory footprint
- Fits on ANY modern smartphone
- ~94% quality retention
Use Cases
- Code generation on mobile IDEs
- Quick text classification / extraction
- Embedded assistants in apps
- Ultra-low-latency responses (<50ms per token)
- Batch processing at massive scale
Quick Start
huggingface-cli download dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 --local-dir ./models
./build/bin/main -m ./models/model.gguf -p "Explain quantum computing simply." -n 128 -t 4