SmolVLM Instruct 4bit is an open-source language model by mlx-community. Features: 464.9m LLM, VRAM: 1.5GB, License: apache-2.0, Quantized, Instruction-Based.
| LLM Name | SmolVLM Instruct 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/SmolVLM-Instruct-4bit |
| Base Model(s) | |
| Model Size | 464.9m |
| Required VRAM | 1.5 GB |
| Updated | 2026-08-08 |
| Maintainer | mlx-community |
| Model Type | idefics3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Idefics3ForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 16384 |
| Transformers Version | 4.46.0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 49155 |
| Torch Data Type | bfloat16 |