SmolVLM2 256M Video Instruct is an open-source language model by HuggingFaceTB. Features: 256m LLM, VRAM: 1GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.23.
| LLM Name | SmolVLM2 256M Video Instruct |
| Repository 🤗 | https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct |
| Base Model(s) | |
| Model Size | 256m |
| Required VRAM | 1 GB |
| Updated | 2026-08-09 |
| Maintainer | HuggingFaceTB |
| Model Type | smolvlm |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | SmolVLMForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 8192 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 49280 |
| Torch Data Type | float32 |