Model reference · open weights
rubert-cased-conversational is an open-weight embedding model from DeepPavlov. rubert-base-cased-conversational (BF16) weighs 714 MB; the smallest configuration that runs it is RTX 3060 12 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the DeepPavlov/rubert-base-cased-conversational model card, 2026-10-01
What it is
| Released by | DeepPavlov |
|---|---|
| Released | 2022-03-02 |
| VRAM | 714 MB for the weights |
What it runs on
| Card | Runs | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
Conversational RuBERT (Russian, cased, 12‑layer, 768‑hidden, 12‑heads, 180M parameters) was trained on OpenSubtitles[1], Dirty, Pikabu, and a Social Media segment of Taiga corpus[2]. We assembled a new vocabulary for Conversational RuBERT model on this data and initialized the model with RuBERT.
08.11.2021: upload model with MLM and NSP heads
[1]: P. Lison and J. Tiedemann, 2016, OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles. In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016)
[2]: Shavrina T., Shapovalova O. (2017) TO THE METHODOLOGY OF CORPUS CONSTRUCTION FOR MACHINE LEARNING: «TAIGA» SYNTAX TREE CORPUS AND PARSER. in proc. of “CORPORA2017”, international conference , Saint-Petersbourg, 2017.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.