Model Intelligence Sheet
ggml-org/SmolVLM2-256M-Video-Instruct-GGUF overview
SmolVLM2 256M Video Instruct Run it in the Llama app: https://llama.app Or from the terminal: bash llama serve hf ggml org/SmolVLM2 256M Video Instruct GGUF So…
Runs locally from ~99.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
7 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| SmolVLM2-256M-Video-Instruct-BF16.gguf | GGUF | BF16 | 312.6 MB | Download |
| SmolVLM2-256M-Video-Instruct-Q4_K_M.gguf | GGUF | Q4_K_M | 125.2 MB | Download |
| SmolVLM2-256M-Video-Instruct-Q8_0.gguf | GGUF | Q8_0 | 166.9 MB | Download |
| SmolVLM2-256M-Video-Instruct-f16.gguf | GGUF | F16 | 312.6 MB | Download |
| mmproj-SmolVLM2-256M-Video-Instruct-BF16.gguf | GGUF | BF16 | 181.2 MB | Download |
| mmproj-SmolVLM2-256M-Video-Instruct-Q8_0.gguf | GGUF | Q8_0 | 99.0 MB | Download |
| mmproj-SmolVLM2-256M-Video-Instruct-f16.gguf | GGUF | F16 | 181.2 MB | Download |
Model Details
| Model ID | ggml-org/SmolVLM2-256M-Video-Instruct-GGUF |
|---|---|
| Author | ggml-org |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | HuggingFaceTB/SmolVLM2-256M-Video-Instruct |
| Last modified | 2026-10-19T15:36:02.000Z |
Model README
---
license: apache-2.0
pipeline_tag: image-text-to-text
tags:
- gguf
- quantized
base_model:
- HuggingFaceTB/SmolVLM2-256M-Video-Instruct
---
SmolVLM2-256M-Video-Instruct
Run it in the Llama app: https://llama.app
Or from the terminal:
llama serve -hf ggml-org/SmolVLM2-256M-Video-Instruct-GGUFSource models
- https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct
> [!IMPORTANT]
> This model is automatically converted using https://github.com/ggml-org/convert
Run ggml-org/SmolVLM2-256M-Video-Instruct-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models