Loading…
Loading…
Models / MiniLM-L6-H384-uncased / MiniLM-L6-H384-uncased
Embeddings · served with Text Embeddings Inference · ↓ 180 downloads a month · View on Hugging Face
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 |
|---|---|---|---|---|
| all MiniLM L6 v2 (sentence-transformers)sentence-transformers/all-MiniLM-L6-v2 | Text Embeddings Inference | 50 MB | 1.6 GB | $0.08/h RTX 3060 |
| all MiniLM L6 v2 (Xenova)Xenova/all-MiniLM-L6-v2 | ONNX Runtime | 20 MB | 1 GB | $0.08/h GTX 1660 SUPER |
| zlm v1 iab classify edge (zgpu-ai)zgpu-ai/zlm-v1-iab-classify-edge | ONNX Runtime | 20 MB | 1 GB | $0.08/h GTX 1660 SUPER |
| all MiniLM L6 v2 ONNX (onnx-community)onnx-community/all-MiniLM-L6-v2-ONNX | ONNX Runtime | 30 MB | 1 GB | $0.08/h GTX 1660 SUPER |
| all MiniLM L6 v2 code search 512 (isuruwijesiri)isuruwijesiri/all-MiniLM-L6-v2-code-search-512 | Text Embeddings Inference | 50 MB | 1.6 GB | $0.08/h RTX 3060 |
| smart tab embedding (Mozilla)Mozilla/smart-tab-embedding | Text Embeddings Inference | 50 MB | 1.6 GB | $0.08/h RTX 3060 |
| all MiniLM L6 v2 (KnightsAnalytics)KnightsAnalytics/all-MiniLM-L6-v2 | ONNX Runtime | 90 MB | 1.1 GB | $0.08/h GTX 1660 SUPER |
| tradexcel assistant encoder (adiikj)adiikj/tradexcel-assistant-encoder | ONNX Runtime | 20 MB | 1 GB | $0.08/h GTX 1660 SUPER |
| pocket embed 22m 128 (pocket-mind)pocket-mind/pocket-embed-22m-128 | Text Embeddings Inference | 50 MB | 1.6 GB | $0.08/h RTX 3060 |
| all MiniLM L6 v2 onnx (monju-lab)monju-lab/all-MiniLM-L6-v2-onnx | ONNX Runtime | 20 MB | 1 GB | $0.08/h GTX 1660 SUPER |
Deploying embedding and reranking models (Text Embeddings Inference) is coming soon.
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.