Ettin Reranker 68M — GGUF
GGUF quantizations of cross-encoder/ettin-reranker-68m-v1, a ModernBERT-based cross-encoder reranker (68.6M params, Apache-2.0).
Converted with CrispEmbed.
Files
| File | Quant | Size |
|---|---|---|
| F32 | 275 MB | |
| Q8_0 | 75 MB | |
| Q4_K | 54 MB |
Architecture
- Base: ModernBERT (19 layers, 512 hidden)
- Classifier head: Dense(512→512, GELU) → LayerNorm → Dense(512→1)
- Tokenizer: GPT-2 ByteLevel BPE (50368 tokens)
Usage
- Downloads last month
- 169
Hardware compatibility
Log In to add your hardware
6-bit
8-bit
32-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for cstr/ettin-reranker-68m-v1-GGUF
Base model
jhu-clsp/ettin-encoder-68m Quantized
cross-encoder/ettin-reranker-68m-v1