SAVRN Model Hub · Comparisons
Florence-2-base vs surya-ocr-2
Florence-2-base has 232M parameters and surya-ocr-2 has 686M parameters; Florence-2-base is released under MIT License and surya-ocr-2 under Open RAIL License; at 16-bit, Florence-2-base needs about 0.6 GB (1x MI300X from $1.85 an hour) and surya-ocr-2 about 1.6 GB (1x MI300X from $1.85 an hour).
| Field | Florence-2-base microsoft/Florence-2-base | surya-ocr-2 datalab-to/surya-ocr-2 |
|---|---|---|
| Publisher | Microsoft | Datalab |
| Task | Image and text to text | Image and text to text |
| Modality | Image and text | Image and text |
| Parameters, as reported | 232M parameters | 686M parameters |
| Architecture | Florence2ForConditionalGeneration | Qwen3_5ForConditionalGeneration |
| Library | transformers | transformers |
| Context length | 1,024 tokens | 262,144 tokens |
| Repository size | 930.3 MB | 1.4 GB |
| Artifact formats | safetensors, pytorch | safetensors |
| License | mit | openrail |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.6 GB | 1.6 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 | 0.4 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 5ca5edf5bd01 | 3b3d4cdf88d6 |
| Downloads reported by the hub | 3.1M | 1.4M |
| Last observed | 2026-10-09 | 2026-10-09 |
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.
Other Reported Results
These results are listed for each model on its own, because the conditions needed to compare them are not stated or do not match. Two results that leave a condition blank are not assumed to share it.
surya-ocr-2
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| allenai/olmOCR-bench | Task arxiv_mathMetric arxiv_mathComparison conditions not established | 88.3 | Surya OCR 2 Model Card Reported by a third party |
Evaluated revision not stated | 2026-05-27 |
| allenai/olmOCR-bench | Task baselineMetric baselineComparison conditions not established | 99.7 | Surya OCR 2 Model Card Reported by a third party |
Evaluated revision not stated | 2026-05-27 |
| allenai/olmOCR-bench | Task headers_footersMetric headers_footersComparison conditions not established | 92.5 | Surya OCR 2 Model Card Reported by a third party |
Evaluated revision not stated | 2026-05-27 |
| allenai/olmOCR-bench | Task long_tiny_textMetric long_tiny_textComparison conditions not established | 93.7 | Surya OCR 2 Model Card Reported by a third party |
Evaluated revision not stated | 2026-05-27 |
| allenai/olmOCR-bench | Task multi_columnMetric multi_columnComparison conditions not established | 82.4 | Surya OCR 2 Model Card Reported by a third party |
Evaluated revision not stated | 2026-05-27 |
| allenai/olmOCR-bench | Task old_scansMetric old_scansComparison conditions not established | 41.8 | Surya OCR 2 Model Card Reported by a third party |
Evaluated revision not stated | 2026-05-27 |
| allenai/olmOCR-bench | Task old_scans_mathMetric old_scans_mathComparison conditions not established | 81.4 | Surya OCR 2 Model Card Reported by a third party |
Evaluated revision not stated | 2026-05-27 |
| allenai/olmOCR-bench | Task overallMetric overallComparison conditions not established | 83.3 | Surya OCR 2 Model Card Reported by a third party |
Evaluated revision not stated | 2026-05-27 |
| allenai/olmOCR-bench | Task table_testsMetric table_testsComparison conditions not established | 86.6 | Surya OCR 2 Model Card Reported by a third party |
Evaluated revision not stated | 2026-05-27 |
| llamaindex/ParseBench | Task chartMetric chartSetup Pipeline name: surya2_sdkComparison conditions not established | 21.95 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-06-01 |
| llamaindex/ParseBench | Task layoutMetric layoutSetup Pipeline name: surya2_sdkComparison conditions not established | 71.59 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-06-01 |
| llamaindex/ParseBench | Task meanMetric meanSetup Pipeline name: surya2_sdkComparison conditions not established | 64.83 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-06-01 |
| llamaindex/ParseBench | Task tableMetric tableSetup Pipeline name: surya2_sdkComparison conditions not established | 82.68 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-06-01 |
| llamaindex/ParseBench | Task text_contentMetric text_contentSetup Pipeline name: surya2_sdkComparison conditions not established | 86.57 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-06-01 |
| llamaindex/ParseBench | Task text_formattingMetric text_formattingSetup Pipeline name: surya2_sdkComparison conditions not established | 61.36 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-06-01 |
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 surya-ocr-2
A context window of 262,144 tokens on a 686M parameter OCR model tells you what Datalab built it for: whole documents, with layout, reading order and table rows and columns alongside the text. The 16-bit weights are 1.4 GB and need 1.6 GB; 8-bit needs 0.8 GB, 4-bit 0.4 GB. The cheapest setup in our data is one MI300X with 192 GB at $1.85 per hour, so one card runs many instances side by side and the buying question is pages per hour per dollar.
Open RAIL permits commercial use subject to use-based restrictions you must pass on to anyone who receives the model or a derivative, so read that list before it goes into a product. Then check the model card's own olmOCR-bench numbers, 83.3 overall but 41.8 on old scans, against your scanned backfile. The publisher calls it 650M parameters while the configuration counts 686M.
Questions
Which is larger, Florence-2-base or surya-ocr-2?
surya-ocr-2 (686M 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 surya-ocr-2?
At 4-bit, Florence-2-base fits on 1x MI300X from $1.85 an hour and surya-ocr-2 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 surya-ocr-2 commercially?
Yes, with conditions. surya-ocr-2 is released under Open RAIL License. Open RAIL licenses permit use, including commercial use, subject to the use-based restrictions listed in the license, which must be passed on to anyone who receives the model or a derivative.