cstr/ettin-reranker-17m-v1-GGUF overview
Ettin Reranker 17M — GGUF GGUF quantizations of cross encoder/ettin reranker 17m v1 https://huggingface.co/cross encoder/ettin reranker 17m v1 , a ModernBERT b…
Runs locally from ~16.6 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
Model README
---
license: apache-2.0
base_model: cross-encoder/ettin-reranker-17m-v1
tags:
- gguf
- reranker
- cross-encoder
- modernbert
- crispembed
library_name: crispembed
---
Ettin Reranker 17M — GGUF
GGUF quantizations of cross-encoder/ettin-reranker-17m-v1, a ModernBERT-based cross-encoder reranker (17.6M params, Apache-2.0).
Converted with CrispEmbed.
Files
| File | Quant | Size |
|------|-------|------|
| | F32 | 69 MB |
| | Q8_0 | 19 MB |
| | Q4_K | 17 MB |
Architecture
- Base: ModernBERT (7 layers, 256 hidden)
- Classifier head: Dense(256→256, GELU) → LayerNorm → Dense(256→1)
- Tokenizer: GPT-2 ByteLevel BPE (50368 tokens)
Usage
Run cstr/ettin-reranker-17m-v1-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models