Loading…
Loading…
Models / ruri-v3-pt
4 models (30M to 310M) · ↓ 1.2M downloads a month · from $0.08/h on GTX 1660 SUPER 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 |
|---|---|---|---|---|
| Originalcl-nagoya/ruri-v3-pt-30m | Text Embeddings Inference | 70 MB | 1.6 GB | $0.08/h GTX 1660 SUPER |
| ruri v3 30mcl-nagoya/ruri-v3-30m | Text Embeddings Inference | 70 MB | 1.6 GB | $0.08/h GTX 1660 SUPER |
| japanese reranker xsmall v2 (hotchpotch)hotchpotch/japanese-reranker-xsmall-v2 | Text Embeddings Inference | 70 MB | 1.6 GB | $0.08/h GTX 1660 SUPER |
| ruri v3 30m ONNX (sirasagi62)sirasagi62/ruri-v3-30m-ONNX | ONNX Runtime | 40 MB | 1.1 GB | $0.08/h GTX 1660 SUPER |
| ruri v3 30m ONNX (onnx-community)onnx-community/ruri-v3-30m-ONNX | ONNX Runtime | 40 MB | 1.1 GB | $0.08/h GTX 1660 SUPER |
| japanese reranker tiny v2 (hotchpotch)hotchpotch/japanese-reranker-tiny-v2 | Text Embeddings Inference | 60 MB | 1.6 GB | $0.08/h GTX 1660 SUPER |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalcl-nagoya/ruri-v3-pt-70m | Text Embeddings Inference | 140 MB | 1.7 GB | $0.08/h GTX 1660 SUPER |
| ruri v3 70mcl-nagoya/ruri-v3-70m | Text Embeddings Inference | 140 MB | 1.7 GB | $0.08/h GTX 1660 SUPER |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalcl-nagoya/ruri-v3-pt-130m | Text Embeddings Inference | 260 MB | 1.8 GB | $0.08/h GTX 1660 SUPER |
| ruri v3 130mcl-nagoya/ruri-v3-130m | Text Embeddings Inference | 260 MB | 1.8 GB | $0.08/h GTX 1660 SUPER |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalcl-nagoya/ruri-v3-pt-310m | Text Embeddings Inference | 630 MB | 2.3 GB | $0.08/h GTX 1660 SUPER |
| ruri v3 310mcl-nagoya/ruri-v3-310m | Text Embeddings Inference | 630 MB | 2.3 GB | $0.08/h GTX 1660 SUPER |
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").