SmolLM 1.7B
by Hugging Face · open-source · Last verified 2026-03-17
SmolLM 1.7B is Hugging Face's compact and highly capable language model trained on a curated dataset called SmolLM-Corpus consisting of high-quality web, code, and math data. It achieves remarkable performance for its size and was designed specifically for efficient on-device deployment and real-time inference.
https://huggingface.co/HuggingFaceTB/SmolLM-1.7B ↗C
C—Below Average
Adoption: C+Quality: B+Freshness: ACitations: CEngagement: F
Specifications
- License
- Apache 2.0
- Pricing
- open-source
- Capabilities
- text-generation, code-generation, math-reasoning, on-device-inference
- Integrations
- Hugging Face, Transformers.js, Ollama
- Use Cases
- browser-side AI inference, mobile AI assistants, code completion on device, offline AI applications
- API Available
- Yes
- Parameters
- ~1.7B
- Context Window
- 2K
- Modalities
- text
- Training Cutoff
- 2024
- Tags
- small, edge, huggingface, efficient, on-device
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
48.4Adoption
55
Quality
72
Freshness
82
Citations
48
Engagement
0