---

license: apache-2.0

base_model: cross-encoder/ettin-reranker-150m-v1

tags:

- gguf

- reranker

- cross-encoder

- modernbert

- crispembed

library_name: crispembed

---

Ettin Reranker 150M — GGUF

GGUF quantizations of cross-encoder/ettin-reranker-150m-v1, a ModernBERT-based cross-encoder reranker (150M params, Apache-2.0).

Converted with CrispEmbed convert-bert-to-gguf.py.

Files

| File | Quant | Size | Notes |

|------|-------|------|-------|

| ettin-reranker-150m-v1-f32.gguf | F32 | 572 MB | Full precision |

| ettin-reranker-150m-v1-f16.gguf | F16 | 288 MB | Half precision (identical scores to f32) |

| ettin-reranker-150m-v1-q8_0.gguf | Q8_0 | 155 MB | 8-bit (scores within 0.06) |

| ettin-reranker-150m-v1-q4_k.gguf | Q4_K | 102 MB | 4-bit (scores within 0.12) |

Quality (vs Python CrossEncoder reference)

| Quant | France+ | France- | Pasta+ | Pasta- |

|-------|---------|---------|--------|--------|

| Reference | +11.85 | -4.41 | +7.79 | -5.57 |

| F32 | +11.59 | -4.11 | +7.23 | -5.25 |

| F16 | +11.59 | -4.11 | +7.23 | -5.25 |

| Q8_0 | +11.57 | -4.10 | +7.19 | -5.30 |

| Q4_K | +11.50 | -4.13 | +7.17 | -5.35 |

Ranking is perfectly preserved across all quantizations.

Per-stage diff harness (f32 GGUF vs PyTorch): all 23 stages PASS, structural gate cos=1.000000, worst per-layer cos=0.999760.

Usage

# Rerank
crispembed -m ettin-reranker-150m-v1-q4_k.gguf --rerank-query "What is AI?" --rerank-doc "Artificial intelligence is..."

# C API
float score = crispembed_rerank(ctx, "query", "document");

# Batch rerank
int n = crispembed_rerank_batch(ctx, "query", docs, n_docs, scores);

Architecture

• Base: ModernBERT (22 layers, 768 hidden, 12 heads)
• Classifier head: Dense(768→768, GELU) → LayerNorm → Dense(768→1)
• Attention: alternating global/sliding (window=128), RoPE theta=160000
• Tokenizer: GPT-2 ByteLevel BPE (50368 tokens)