Loading…
Loading…
Models / e5-mistral
1 model (7B) · ↓ 937.4K 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 |
|---|---|---|---|---|
| Originalintfloat/e5-mistral-7b-instruct | Text Embeddings Inference | 14 GB | 20 GB | $0.23/h RTX 3080 |
| bnb 4bit (gabor-hosu)gabor-hosu/e5-mistral-7b-instruct-bnb-4bit | Text Embeddings Inference | 3.9 GB | 6.5 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").