Loading…
Loading…
Models / multilingual-e5-large
2 models (~560M to ~560M) · ↓ 8.3M 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 |
|---|---|---|---|---|
| Originalintfloat/multilingual-e5-large | Text Embeddings Inference | 1.1 GB | 3 GB | $0.08/h GTX 1660 SUPER |
| Main (Xenova)Xenova/multilingual-e5-large | ONNX Runtime | 560 MB | 1.8 GB | $0.08/h GTX 1660 SUPER |
| nep 16384 (alphaedge-ai)alphaedge-ai/multilingual-e5-large-nep-16384 | Text Embeddings Inference | 640 MB | 2.3 GB | $0.08/h GTX 1660 SUPER |
| Main (denniscraandijk)denniscraandijk/dutch-english-multilingual-e5-large | Text Embeddings Inference | 700 MB | 2.4 GB | $0.08/h GTX 1660 SUPER |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalintfloat/multilingual-e5-large-instruct | Text Embeddings Inference | 1.1 GB | 3 GB | $0.08/h GTX 1660 SUPER |
| mon 16384 (alphaedge-ai)alphaedge-ai/multilingual-e5-large-instruct-mon-16384 | Text Embeddings Inference | 640 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").