Hugging Face engineer Tom Aarsen released the Ettin Reranker series on May 19 — six Apache 2.0 open-source Sentence Transformers CrossEncoders, covering the full range from 17M to 1B. All models are distilled pointwise MSE from the 1.54B mxbai-rerank-large-v2 on the Ettin ModernBERT encoder, with all ~143M (query, document, score) triples in the training data publicly released. Combined with Flash Attention 2 + bf16 inference on H100, the speed is 1.7×-8.3× faster than default loading. On the benchmark side, the 1B model ties the 1.54B teacher on MTEB (eng, v2) Retrieval at 0.6114 (0.0001 difference), and lags by 0.008 on NanoBEIR. The 150M size beats Qwen3-Reranker-0.6B (596M) on MTEB with 0.5994. The smallest 17M beats ms-marco-MiniLM-L12-v2 (33M, 0.5066) on MTEB with 0.5576, the 32M beats bge-reranker-v2-m3 (568M, 0.5526) on MTEB with 0.5779, achieving the upset with a 17× parameter gap. Architecturally it uses unpadded attention, RoPE, GeGLU, and a 4-module classification head, with CLS pooling beating mean pooling, benefiting from ModernBERT's once-every-three-layers global attention. All models support 8192 token context, and can directly drop-in replace the MiniLM series rerankers in existing retrieve-then-rerank stacks.