Downloads · 30 days
58
17% of all-time downloads
ettin-reranker-32m-v1-GGUF
cstr/ettin-reranker-32m-v1-GGUF
ettin-reranker-32m-v1-GGUF is a machine learning model from cstr. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for crispembed. The card lists the license as apache-2.0.
GGUF quantizations of cross-encoder/ettin-reranker-32m-v1, a ModernBERT-based cross-encoder reranker (32.8M params, Apache-2.0).
All-time downloads
333
Public
Repo size
230 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf230 MB · 100%
At a glance
- Library
- crispembed
- License
- apache-2.0
- Access
- Public
- Created
- Aug 22, 2026
- Updated
- Aug 22, 2026
- SHA
- 0c56b158
Base models
Model card
From the Hugging Face model README
Ettin Reranker 32M — GGUF
GGUF quantizations of cross-encoder/ettin-reranker-32m-v1, a ModernBERT-based cross-encoder reranker (32.8M params, Apache-2.0).
Converted with CrispEmbed.
Files
| File | Quant | Size |
|---|---|---|
| F32 | 129 MB | |
| Q8_0 | 36 MB | |
| Q4_K | 29 MB |
Architecture
- Base: ModernBERT (10 layers, 384 hidden)
- Classifier head: Dense(384→384, GELU) → LayerNorm → Dense(384→1)
- Tokenizer: GPT-2 ByteLevel BPE (50368 tokens)
Usage
- Library
- crispembed
- License
- apache-2.0
- Created
- Aug 22, 2026
- Updated
- Aug 22, 2026