Loading…
Loading…
Embeddings · served with ONNX Runtime · ↓ 2.3K downloads a month · View on Hugging Face
Smaller versions (8-bit, 4-bit) need less GPU memory and answer a little less precisely.
The same model packaged differently: a quantized version needs less GPU memory and runs on a cheaper machine.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalBAAI/bge-m3 | ONNX Runtime | 2.3 GB | 4.4 GB | $0.08/h GTX 1660 SUPER |
| Main (Xenova)Xenova/bge-m3 | ONNX Runtime | 570 MB | 1.9 GB | $0.08/h GTX 1660 SUPER |
| Main (antoinelouis)antoinelouis/french-bge-m3 | Text Embeddings Inference | 700 MB | 2.4 GB | $0.08/h RTX 3060 |
| Vietnamese Embedding (AITeamVN)AITeamVN/Vietnamese_Embedding | Text Embeddings Inference | 1.1 GB | 3 GB | $0.08/h RTX 3060 |
| Vietnamese Embedding v2 (AITeamVN)AITeamVN/Vietnamese_Embedding_v2 | Text Embeddings Inference | 1.1 GB | 3 GB | $0.08/h RTX 3060 |
| onnx int8 (gpahal)gpahal/bge-m3-onnx-int8 | ONNX Runtime | 570 MB | 1.9 GB | $0.08/h GTX 1660 SUPER |
Deploying ONNX models from the catalog is coming soon. Today, download the files from Hugging Face and upload them in Inference.
| ONNX (onnx-community)onnx-community/bge-m3-ONNX |
| ONNX Runtime |
| 1 MB |
| 1 GB |
| $0.08/h GTX 1660 SUPER |
| Main (nrl-ai)nrl-ai/vietnamese-embedding-bge-m3 | Text Embeddings Inference | 1.1 GB | 3 GB | $0.08/h RTX 3060 |
| Main (sayed0am)sayed0am/arabic-english-bge-m3 | Text Embeddings Inference | 720 MB | 2.4 GB | $0.08/h RTX 3060 |
| fas 32768 (alphaedge-ai)alphaedge-ai/bge-m3-fas-32768 | Text Embeddings Inference | 690 MB | 2.4 GB | $0.08/h RTX 3060 |
| ces 16384 (alphaedge-ai)alphaedge-ai/bge-m3-ces-16384 | Text Embeddings Inference | 660 MB | 2.4 GB | $0.08/h RTX 3060 |
| Main (cnmoro)cnmoro/portuguese-bge-m3 | Text Embeddings Inference | 700 MB | 2.4 GB | $0.08/h RTX 3060 |
| Main (karmx)karmx/Llama-Karmx-Indic-Embedding-bge-m3 | Text Embeddings Inference | 1.1 GB | 3 GB | $0.08/h RTX 3060 |
| financial matryoshka (haophancs)haophancs/bge-m3-financial-matryoshka | Text Embeddings Inference | 1.1 GB | 3 GB | $0.08/h RTX 3060 |
| Main (NohTow)NohTow/french-bge-m3 | Text Embeddings Inference | 720 MB | 2.4 GB | $0.08/h RTX 3060 |
Prices are per hour for the whole machine and its disk, right now. Speed is Vast's DLPerf score of the machine, relative to the cheapest. Best value: the most speed per dollar. Only machines with a Vast reliability above 95% that download at 400 Mbit/s or more are offered: the machine fetches the model itself.