ai/smollm3
SmolLM3 is a 3.1B model for efficient on-device use, with strong performance in chat
10K+
ai/smollm3 repository overview
SmolLM3
SmolLM3 is a compact 3.1B parameter language model designed for efficient on-device deployment while maintaining strong performance across a wide range of language tasks. Building on the success of the SmolLM series, SmolLM3 delivers improved instruction following, reasoning capabilities, and knowledge retention in a lightweight package. The model is optimized for chat assistants, text processing, and various natural language understanding tasks.
Intended uses
SmolLM3 is designed for:
- Chat assistants and conversational AI
- Text summarization and rewriting
- Question answering and knowledge retrieval
- Code assistance and text generation
- On-device AI applications
Characteristics
| Attribute | Details |
|---|---|
| Provider | Hugging Face |
| Architecture | SmolLM3 |
| Cutoff date | October 2024 |
| Languages | English |
| Tool calling | ✅ |
| Input modalities | Text |
| Output modalities | Text |
| License | Apache 2.0 |
Available model variants
| Model variant | Parameters | Quantization | Context window | VRAM¹ | Size |
|---|---|---|---|---|---|
ai/smollm3:latestai/smollm3:Q4_K_M | 3.1B | MOSTLY_Q4_K_M | 66K tokens | 2.45 GiB | 1.78 GB |
ai/smollm3:F16 | 3.1B | MOSTLY_F16 | 66K tokens | 6.40 GiB | 5.73 GB |
ai/smollm3:Q8_0 | 3.1B | MOSTLY_Q8_0 | 66K tokens | 3.72 GiB | 3.04 GB |
¹: VRAM estimated based on model characteristics.
latest→Q4_K_M
Use this AI model with Docker Model Runner
First, pull the model:
docker model pull ai/smollm3
Then run the model:
docker model run ai/smollm3
For more information on Docker Model Runner, explore the documentation.
Links
Tag summary
Content type
Model
Digest
sha256:9bff8b097…
Size
1.8 GB
Last updated
7 months ago
docker model pull ai/smollm3This week's pulls
Pulls:
479
Last week