SM

smolvla-so101-multi-task

SmolvlaGGUF by khanhnd61Updated 2026-09-25
Download on Hugging Face
Parameters403M
Context—
Layers—
Architecturevla-simd
Smallest quant1.0 GB
Quick answer

smolvla-so101-multi-task needs about 1.6 GB of memory at its main file (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.

smolvla-so101-multi-task is a 403M-parameter Smolvla model in GGUF format, quantized by khanhnd61. The repository has 1 quant file, from 1.0 GB to 1.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.0 GB 1.6 GB
Fits Get file →

What GPU do you need for smolvla-so101-multi-task?

These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (1.0 GB file, about 1.6 GB in use).

Specifications

Architecture from the GGUF header

Architecturevla-simd
Parameters403M

Source

Quantized bykhanhnd61
FamilySmolvla
Licenseapache-2.0
Downloads (HF)56
Last updated2026-09-25

Frequently asked questions about smolvla-so101-multi-task

How much VRAM does smolvla-so101-multi-task need?

About 1.6 GB at its main file with an 8K context window. That is the 1.0 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 smolvla-so101-multi-task on an 8 GB GPU?

Yes, with the smaller files: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of smolvla-so101-multi-task GGUF?

It depends on the quant: file is 1.0 GB.

Where can I download smolvla-so101-multi-task GGUF?

The files are on Hugging Face in the khanhnd61/smolvla-so101-multi-task-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 smolvla-so101-multi-task 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.

Similar models

Browse all →

More from khanhnd61

All by khanhnd61 →

More Smolvla models

All Smolvla →

Other tiny models

All tiny models →