62 models
| Performance | Quality | |||||
|---|---|---|---|---|---|---|
| Model | Params | Throughput | Latency | NDCG@10 | F1 | AP |
| vidore/colqwen2.5-v0.2 Encode · Multi-Vec · Qwen2 | 7.0B | 2.1 img/s | 1.9s | — | — | — |
| vidore/colpali-v1.3-hf Encode · Multi-Vec · PaliGemma | 3.0B | 5.8 img/s | 619.1ms | — | — | — |
| Alibaba-NLP/gte-Qwen2-1.5B-instruct Encode · Dense · | 1.5B | 12.3K tok/s | 261.1ms | — | — | — |
| NovaSearch/stella_en_1.5B_v5 Encode · Dense · | 1.5B | 12.8K tok/s | 265.9ms | — | — | — |
| laion/CLIP-ViT-H-14-laion2B-s32B-b79K Encode · Dense · | 986M | 321.5 img/s | 503.8ms | — | — | — |
| Qwen/Qwen3-Embedding-0.6B Encode · Dense · | 600M | 20.6K tok/s | 156.9ms | — | — | — |
| BAAI/bge-m3 Encode · Dense /Sparse /Multi-Vec · | 568M | 33.2K tok/s | 93.4ms | — | — | — |
| BAAI/bge-m3 Score · Dense /Sparse /Multi-Vec · | 568M | 2.8K tok/s | 56.8ms | — | — | — |
| BAAI/bge-reranker-large Score · Score · | 560M | 6.6K tok/s | 41.4ms | — | — | — |
| intfloat/multilingual-e5-large Encode · Dense · | 560M | 29.8K tok/s | 108.6ms | — | — | — |
| intfloat/multilingual-e5-large-instruct Encode · Dense · | 560M | 29.4K tok/s | 106.9ms | — | — | — |
| EmergentMethods/gliner_large_news-v2.1 Extract · Entities · DeBERTa | 435M | — | — | — | — | — |
| Ihor/gliner-biomed-large-v1.0 Extract · Entities · DeBERTa | 435M | — | — | — | — | — |
| jackboyla/glirel-large-v0 Extract · Relations · DeBERTa | 435M | — | — | — | — | — |
| mixedbread-ai/mxbai-colbert-large-v1 Encode · Multi-Vec · | 435M | 43.3K tok/s | 74.9ms | — | — | — |
| mixedbread-ai/mxbai-colbert-large-v1 Score · Multi-Vec · | 435M | 4.0K tok/s | 45.6ms | — | — | — |
| mixedbread-ai/mxbai-rerank-large-v2 Encode · Score · | 435M | — | — | — | — | — |
| mixedbread-ai/mxbai-rerank-large-v2 Score · Score · | 435M | 2.2K tok/s | 1.4s | — | — | — |
| urchade/gliner_large-v2.1 Extract · Entities · DeBERTa | 435M | — | — | — | — | — |
| urchade/gliner_multi-v2.1 Extract · Entities · DeBERTa | 435M | — | — | — | — | — |
| urchade/gliner_multi_pii-v1 Extract · Entities · DeBERTa | 435M | — | — | — | — | — |
| openai/clip-vit-large-patch14 Encode · Dense · | 428M | 706.0 img/s | 298.1ms | — | — | — |
| NovaSearch/stella_en_400M_v5 Encode · Dense · ModernBERT | 400M | 27.1K tok/s | 115.7ms | — | — | — |
| google/owlv2-base-patch16-ensemble Extract · Bounding Boxes · CLIP | 400M | 1.0 mpix/s | 954.6ms | — | — | — |
| google/siglip-so400m-patch14-224 Encode · Dense · | 400M | 348.1 img/s | 439.8ms | — | — | — |
| google/siglip-so400m-patch14-384 Encode · Dense · | 400M | 354.9 img/s | 488.3ms | — | — | — |
| intfloat/e5-large-v2 Encode · Dense · | 335M | 33.2K tok/s | 86.6ms | — | — | — |
| Alibaba-NLP/gte-multilingual-base Encode · Dense · ModernBERT | 305M | 55.1K tok/s | 63.1ms | — | — | — |
| lightonai/GTE-ModernColBERT-v1 Encode · Multi-Vec · | 305M | 28.0K tok/s | 103.9ms | — | — | — |
| lightonai/GTE-ModernColBERT-v1 Score · Multi-Vec · | 305M | 231 tok/s | 313.4ms | — | — | — |
| lightonai/Reason-ModernColBERT Encode · Multi-Vec · | 305M | 33.0K tok/s | 82.2ms | — | — | — |
| opensearch-project/opensearch-neural-sparse-encoding-doc-v3-gte Encode · Sparse · ModernBERT | 305M | 34.2K tok/s | 93.7ms | — | — | — |
| google/embeddinggemma-300m Encode · Dense · | 300M | 79.6K tok/s | 55.7ms | — | — | — |
| BAAI/bge-reranker-base Score · Score · | 278M | 5.0K tok/s | 33.2ms | — | — | — |
| jinaai/jina-reranker-v2-base-multilingual Score · Score · XLM-RoBERTa | 278M | 8.3K tok/s | 32.0ms | — | — | — |
| IDEA-Research/grounding-dino-base Extract · Bounding Boxes · Swin | 250M | 0.8 mpix/s | 785.8ms | — | — | — |
| laion/CLIP-ViT-B-32-laion2B-s34B-b79K Encode · Dense · | 151M | 1176.0 img/s | 178.6ms | — | — | — |
| openai/clip-vit-base-patch32 Encode · Dense · | 151M | 651.0 img/s | 319.4ms | — | — | — |
| Alibaba-NLP/gte-reranker-modernbert-base Score · Score · | 150M | 6.2K tok/s | 41.9ms | — | — | — |
| mixedbread-ai/mxbai-rerank-base-v2 Encode · Score · | 150M | — | — | — | — | — |
| mixedbread-ai/mxbai-rerank-base-v2 Score · Score · | 150M | 7.0K tok/s | 457.1ms | — | — | — |
| urchade/gliner_medium-v2.1 Extract · Entities · DeBERTa | 150M | — | — | — | — | — |
| nomic-ai/nomic-embed-text-v2-moe Encode · Dense · | 137M | 13.0K tok/s | 149.6ms | — | — | — |
| jinaai/jina-colbert-v2 Encode · Multi-Vec · XLM-RoBERTa | 110M | 28.5K tok/s | 105.7ms | — | — | — |
| jinaai/jina-colbert-v2 Score · Multi-Vec · XLM-RoBERTa | 110M | 1.4K tok/s | 226.1ms | — | — | — |
| naver/splade-cocondenser-selfdistil Encode · Sparse · | 110M | 40.0K tok/s | 72.4ms | — | — | — |
| naver/splade-v3 Encode · Sparse · | 110M | 29.6K tok/s | 83.7ms | — | — | — |
| numind/NuNER_Zero Extract · Entities · DeBERTa | 110M | — | — | — | — | — |
| numind/NuNER_Zero-span Extract · Entities · DeBERTa | 110M | — | — | — | — | — |
| opensearch-project/opensearch-neural-sparse-encoding-doc-v2-distill Encode · Sparse · | 110M | 49.1K tok/s | 63.3ms | — | — | — |
| opensearch-project/opensearch-neural-sparse-encoding-doc-v3-distill Encode · Sparse · | 110M | 50.1K tok/s | 60.7ms | — | — | — |
| opensearch-project/opensearch-neural-sparse-encoding-v2-distill Encode · Sparse · | 110M | 44.2K tok/s | 63.3ms | — | — | — |
| intfloat/e5-base-v2 Encode · Dense · | 109M | 53.2K tok/s | 57.9ms | — | — | — |
| IDEA-Research/grounding-dino-tiny Extract · Bounding Boxes · Swin | 80M | 0.9 mpix/s | 532.6ms | — | — | — |
| urchade/gliner_small-v2.1 Extract · Entities · DeBERTa | 60M | — | — | — | — | — |
| answerdotai/answerai-colbert-small-v1 Encode · Multi-Vec · | 33M | 59.1K tok/s | 47.9ms | — | — | — |
| answerdotai/answerai-colbert-small-v1 Score · Multi-Vec · | 33M | 1.7K tok/s | 121.7ms | — | — | — |
| cross-encoder/ms-marco-MiniLM-L-12-v2 Score · Score · | 33M | 8.2K tok/s | 31.7ms | — | — | — |
| intfloat/e5-small-v2 Encode · Dense · | 33M | 58.3K tok/s | 49.7ms | — | — | — |
| rasyosef/splade-mini Encode · Sparse · | 33M | 56.3K tok/s | 56.0ms | — | — | — |
| mixedbread-ai/mxbai-edge-colbert-v0-32m Encode · Multi-Vec · | 32M | 45.9K tok/s | 59.7ms | — | — | — |
| sentence-transformers/all-MiniLM-L6-v2 Encode · Dense · | 22M | 55.3K tok/s | 53.3ms | — | — | — |