SAVRN Model Hub · Comparisons
opus-mt-fr-en vs t5-small
Opus-mt-fr-en has 75M parameters and t5-small has 61M parameters; both are released under Apache License 2.0; at 16-bit, opus-mt-fr-en needs about 0.2 GB (1x MI300X from $1.85 an hour) and t5-small about 0.1 GB (1x MI300X from $1.85 an hour).
| Field | opus-mt-fr-en Helsinki-NLP/opus-mt-fr-en | t5-small google-t5/t5-small |
|---|---|---|
| Publisher | Helsinki-NLP Research Group | T5 community |
| Task | Translation | Translation |
| Modality | Text | Text |
| Parameters, as reported | 75M parameters | 61M parameters |
| Architecture | MarianMTModel | T5ForConditionalGeneration |
| Library | transformers | transformers |
| Context length | 512 tokens | Not stated |
| Repository size | 1.2 GB | 2.2 GB |
| Artifact formats | safetensors, pytorch, jax, tf | safetensors, onnx, pytorch, jax, rust, tf |
| License | apache-2.0 | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.2 GB | 0.1 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0 GB | 0 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | c4aed37b318c | df1b051c4962 |
| Downloads reported by the hub | 860.9k | 25M |
| Last observed | 2026-09-18 | 2026-09-19 |
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 opus-mt-fr-en
French in, English out, nothing else. That narrow job is why this 75M-parameter Marian model from the Helsinki-NLP Research Group needs 0.2 GB of memory at 16-bit and 0.1 GB at 8-bit. Against the cheapest card in our table, a 192 GB MI300X at $1.85 an hour, the card is the wrong unit; size a deployment by how many translation streams one card carries. The 512-token window means long documents get split before they go in.
The license is Apache 2.0: commercial use, modification and redistribution are all permitted, with the license and copyright notices kept. Check two things. The repository ships safetensors, pytorch, jax and tf formats and weighs 1.2 GB on disk while the loaded 16-bit weights are 0.2 GB, so pull only the format you serve. And the weights date to March 2022, last touched November 2025, trained on the OPUS corpus, so test your own domain text first.
SAVRN's Notes on t5-small
The 4-bit row reads 0.0 GB and the 16-bit row 0.1 GB, so quantizing buys nothing worth the trouble. The cheapest setup we list is a 192 GB MI300X at $1.85 an hour, which makes the only hardware question what else that card does. What you get is the 61M-parameter checkpoint of the text-to-text transfer transformer, pretrained on C4 with a mix of unsupervised and supervised tasks, labeled for translation.
Apache 2.0 means you can fine-tune it, ship the result and sell it, keeping the notices and stating what you changed. No context length is listed, so measure your longest input against the model yourself. The seven papers listed for it are task datasets, acceptability judgments, semantic textual similarity, inference, SQuAD, word in context, reading comprehension and yes-or-no questions, the trail for what the supervised side covered. The last update was 2023-06-30.
Questions
Which is larger, opus-mt-fr-en or t5-small?
opus-mt-fr-en (75M parameters) is larger than t5-small (61M parameters), by the parameter counts their publishers report.
Which is cheaper to run, opus-mt-fr-en or t5-small?
At 4-bit, opus-mt-fr-en fits on 1x MI300X from $1.85 an hour and t5-small on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use opus-mt-fr-en commercially?
Yes. opus-mt-fr-en 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.
Can I use t5-small commercially?
Yes. t5-small 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.