SAVRN Model Hub · Comparisons
Florence-2-base vs SmolVLM2-500M-Video-Instruct
Florence-2-base has 232M parameters and SmolVLM2-500M-Video-Instruct has 507M parameters; Florence-2-base is released under MIT License and SmolVLM2-500M-Video-Instruct under Apache License 2.0; at 16-bit, Florence-2-base needs about 0.6 GB (1x MI300X from $1.85 an hour) and SmolVLM2-500M-Video-Instruct about 1.2 GB (1x MI300X from $1.85 an hour).
| Field | Florence-2-base microsoft/Florence-2-base | SmolVLM2-500M-Video-Instruct HuggingFaceTB/SmolVLM2-500M-Video-Instruct |
|---|---|---|
| Publisher | Microsoft | Hugging Face Smol Models Research |
| Task | Image and text to text | Image and text to text |
| Modality | Image and text | Image and text |
| Parameters, as reported | 232M parameters | 507M parameters |
| Architecture | Florence2ForConditionalGeneration | SmolVLMForConditionalGeneration |
| Library | transformers | transformers |
| Context length | 1,024 tokens | 8,192 tokens |
| Repository size | 930.3 MB | 7.9 GB |
| Artifact formats | safetensors, pytorch | safetensors, onnx |
| License | mit | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.6 GB | 1.2 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.1 GB | 0.3 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 5ca5edf5bd01 | 7b375e1b73b1 |
| Downloads reported by the hub | 3M | 1.3M |
| Last observed | 2026-09-18 | 2026-09-18 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
SAVRN's Notes on Florence-2-base
Hand it an image and a short text prompt and it returns text; Microsoft's examples are captioning, object detection and segmentation. At 232M parameters the 16-bit weights are 0.5 GB and the run needs 0.6 GB; 8-bit and 4-bit trim that to 0.3 GB and 0.1 GB. Our Index prices the cheapest qualifying card, a single 192 GB MI300X, at $1.85 an hour on-demand, which this would leave nearly empty, so the question is what else shares it.
MIT is the license: commercial use, modification and redistribution, with the copyright and permission notices kept in the package and nothing else to pass downstream. Access is open. Check the context and the revision. Context is 1,024 tokens: room for a task prompt and a caption back, not long text. The files were last updated 2025-08-04, over a year after the 2024-06-15 release, so pin the revision you tested.
SAVRN's Notes on SmolVLM2-500M-Video-Instruct
Ask this model what happens in a clip and it answers from 507M parameters. At 16-bit the weights load in 1.0 GB and need 1.2 GB; 8-bit needs 0.6 GB, 4-bit 0.3 GB, and the publisher puts video inference at 1.8 GB of GPU RAM. The cheapest metered host in our data is one MI300X with 192 GB at $1.85 per hour, so the hardware question is how many copies you pack per card. Context is 8,192 tokens.
Apache 2.0 permits commercial use, modification and redistribution provided the license, copyright notices and any NOTICE file travel with it. Two checks before committing: the repository is 38 files and 7.9 GB because it ships safetensors and ONNX, well above the 1.0 GB you load, and it is quantized from SmolVLM-500M-Instruct and trained on seven listed sets including the_cauldron, Docmatix and LLaVA-Video-178K, which your data policy should clear.
Questions
Which is larger, Florence-2-base or SmolVLM2-500M-Video-Instruct?
SmolVLM2-500M-Video-Instruct (507M parameters) is larger than Florence-2-base (232M parameters), by the parameter counts their publishers report.
Which is cheaper to run, Florence-2-base or SmolVLM2-500M-Video-Instruct?
At 4-bit, Florence-2-base fits on 1x MI300X from $1.85 an hour and SmolVLM2-500M-Video-Instruct on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Florence-2-base commercially?
Yes. Florence-2-base is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
Can I use SmolVLM2-500M-Video-Instruct commercially?
Yes. SmolVLM2-500M-Video-Instruct is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.