SM

SmolVLM2 500M Video Instruct

SmolvlmGGUF by ggml-orgUpdated 2025-04-30
Download on Hugging Face
Parameters409M
Context8K
Layers32
Architecturellama
Smallest quant0.4 GB
Quick answer

SmolVLM2 500M Video Instruct needs about 1.3 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q8_0) to 0.8 GB (F16).

SmolVLM2 500M Video Instruct – lightweight multimodal model for video, image, and text tasks

SmolVLM2 500M Video Instruct is a 0.409B parameter multimodal model based on the Idefics3 architecture. It accepts text, images, and video inputs and generates text responses. The model is licensed under Apache 2.0 and supports vision but not image or video generation.

Good at

  • Video and image question answering
  • Visual captioning and storytelling
  • Interleaved media and text inference

Limits

  • No image or video generation
  • Requires 1.8GB GPU RAM for video inference
  • No support for non‑English languages

Best for

  • On‑device video analysis
  • Multimodal chat assistants
  • Captioning short video clips

Who it’s for. Developers building lightweight multimodal applications that need video or image understanding on limited hardware. The model is suitable for edge devices and mobile deployments where GPU memory is constrained.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.4 GB 1.3 GB
Fits Get file →
F160.8 GB 1.7 GB
Fits Get file →

For 8‑GB VRAM, use the Q8_0 quant (0.44 GB file, ~1.3 GB memory at 8k context). If 4‑GB VRAM is available, the F16 quant (0.82 GB file, ~1.7 GB memory) is the next best option. Both are approximate estimates.

What GPU do you need for SmolVLM2 500M Video Instruct?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (0.8 GB file, about 1.7 GB in use).

Which SmolVLM2 500M Video Instruct quant should you choose?

Q8_0 (0.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters409M
Layers32
Trained context8,192 tokens
KV cache (fp16)40 KB per token

Source

Quantized byggml-org
FamilySmolvlm
Licenseapache-2.0
Downloads (HF)20,962
Last updated2025-04-30

Frequently asked questions about SmolVLM2 500M Video Instruct

How much VRAM does SmolVLM2 500M Video Instruct need?

About 1.3 GB at Q8_0 with an 8K context window. That is the 0.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run SmolVLM2 500M Video Instruct on an 8 GB GPU?

Yes, with F16: the 0.8 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SmolVLM2 500M Video Instruct GGUF?

It depends on the quant: Q8_0 is 0.4 GB, F16 is 0.8 GB.

What context length does SmolVLM2 500M Video Instruct support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.3 GB at 8K.

Where can I download SmolVLM2 500M Video Instruct GGUF?

The files are on Hugging Face in the ggml-org/SmolVLM2-500M-Video-Instruct-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does SmolVLM2 500M Video Instruct use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run SmolVLM2 on 8 GB VRAM?

Yes, the Q8_0 quant uses about 1.3 GB of VRAM at 8k context, fitting comfortably in 8 GB.

Does the model support image generation?

No, SmolVLM2 does not support image or video generation.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of SmolVLM2-500M-Video-Instruct

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Smolvlm models

All Smolvlm →

Other tiny models

All tiny models →