Model reference · open weights
tct_colbert-hnp-msmarco is an open-weight embedding model from castorini. tct_colbert-v2-hnp-msmarco (BF16) weighs 438 MB; the smallest configuration that runs it is RTX 3060 12 GB.
Summary of the castorini/tct_colbert-v2-hnp-msmarco model card, 2026-10-01
What it is
| Released by | castorini |
|---|---|
| Released | 2022-03-02 |
| VRAM | 438 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
This model is to reproduce a variant of TCT-ColBERT-V2 dense retrieval models described in the following paper:
Sheng-Chieh Lin, Jheng-Hong Yang, and Jimmy Lin. In-Batch Negatives for Knowledge Distillation with Tightly-CoupledTeachers for Dense Retrieval. RepL4NLP 2021.
You can find our reproduction report in Pyserini here.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.