Loading…
Loading…
Models / ettin-encoder
GPU memory needed (smallest version of each): ettin-encoder 17M about 1.5 GB, ettin-encoder 32M about 1.6 GB, ettin-encoder 68M about 1.7 GB, ettin-encoder 150M about 1.9 GB, ettin-encoder 400M about 2.4 GB. The cheapest runs on RTX 3060 from $0.09/h right now.
5 models (17M to 400M) · ↓ 67.1K downloads a month · from $0.09/h on RTX 3060 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| ettin reranker 17m v1 (cross-encoder)cross-encoder/ettin-reranker-17m-v1 | vLLM | 30 MB | 1.5 GB | $0.09/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| ettin reranker 32m v1 (cross-encoder)cross-encoder/ettin-reranker-32m-v1 | vLLM | 60 MB | 1.6 GB | $0.09/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| ettin reranker 68m v1 (cross-encoder)cross-encoder/ettin-reranker-68m-v1 | vLLM | 140 MB | 1.7 GB | $0.09/h RTX 3060 |
| prompt guard 68m (sheltron-ai)sheltron-ai/prompt-guard-68m | vLLM | 140 MB | 1.7 GB | $0.09/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| ettin reranker 150m v1 (cross-encoder)cross-encoder/ettin-reranker-150m-v1 | vLLM | 300 MB | 1.9 GB | $0.09/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| ettin reranker 400m v1 (cross-encoder)cross-encoder/ettin-reranker-400m-v1 | vLLM | 790 MB | 2.4 GB | $0.09/h RTX 3060 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").