Model reference · open weights
specter is an open-weight embedding model from allenai. specter (BF16) weighs 440 MB; the smallest configuration that runs it is RTX 3060 12 GB.
Summary of the allenai/specter model card, 2026-10-01
What it is
| Released by | allenai |
|---|---|
| Released | 2022-03-02 |
| VRAM | 440 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
SPECTER is a pre-trained language model to generate document-level embedding of documents. It is pre-trained on a powerful signal of document-level relatedness: the citation graph. Unlike existing pretrained language models, SPECTER can be easily applied to downstream applications without task-specific fine-tuning.
If you're coming here because you want to embed papers, SPECTER has now been superceded by SPECTER2. Use that instead.
Paper: SPECTER: Document-level Representation Learning using Citation-informed Transformers
Original Repo: Github
Evaluation Benchmark: SciDocs
Authors: Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, Daniel S. Weld
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.