HuggingFaceTB/SmolVLM-256M-Instruct
Parameters256M
Context8K
Input → outputimage + text → text
Licenseapache-2.0
PrecisionBF16 · quantized
ArchitectureIdefics3ForConditionalGeneration
ReleasedJan 17, 2025
Downloads346.5K
Based on HuggingFaceTB/SmolLM2-135M-Instruct
Other sizes and formats in the family
| Model | Params | Precision | Downloads |
|---|---|---|---|
| HuggingFaceTB/SmolVLM-Base | 2.2B | BF16 | 599 |
| HuggingFaceTB/SmolVLM-Instructquantized | 2.2B | BF16 | 24.2K |
| HuggingFaceTB/SmolVLM-500M-Base | 507M | BF16 | 278 |
| HuggingFaceTB/SmolVLM-500M-Instructquantized | 507M | BF16 | 128.6K |
| HuggingFaceTB/SmolVLM-256M-Base | 256M | BF16 | 443 |
Built on this model
| Model | Params | Precision | Downloads |
|---|---|---|---|
| HuggingFaceTB/SmolVLM2-256M-Video-Instructquantized | 256M | F32 | 37.1K |
This release in the news
No coverage of this exact release yet.