all-MiniLM-L6-v2 vs multilingual-e5-large-onnx
Specs, VRAM requirements and download trends — updated 23 October 2026.
sentence-transformers · A · Open weights
Params
20 M
Context
512
30d
198.6 M
apache-2.0 · commercial OK
Qdrant · B · Open weights
Params
—
Context
512
30d
647 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | all-MiniLM-L6-v2 | multilingual-e5-large-onnx |
|---|---|---|
| Parameters | 20 M | — |
| Architecture | BertModel | XLMRobertaModel |
| Context length | 512 | 512 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 198,627,085 | 646,679 |
| Downloads all time | 4.1 B | 3.1 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2024-01-16 |
Download trend
Daily snapshots, last 88 days (28 Jul – 23 Oct)
259.7 M390 K
all-MiniLM-L6-v2
multilingual-e5-large-onnx
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
all-MiniLM-L6-v2 · fp16
0.6 GB / 24 GB