Embeddings and rerankers · Mixedbread
mxbai-rerank-large v2
1.5B reranker trained with RL; Apache-2.0.
Datasheet
Maker | Mixedbread |
|---|---|
Parameters | 1.54 BVerifiedsafetensors.total from the HF API Source |
Licence | Apache-2.0Verified |
Access | Public download |
Task (HF pipeline) | text-ranking |
First published on HF | 2025-03-03 |
Last updated on HF | 2026-04-08 |
Weights in memory | 3.1 GB at 16-bit · 0.9 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build. |
Benchmark
Not yet measured
MTEB-R (reranking)
No comparable public score for this benchmark yet. We will not estimate one.
The description summarises the model card at https://huggingface.co/mixedbread-ai/mxbai-rerank-large-v2. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.