all-MiniLM-L6-v2 vs embeddinggemma-300m-ONNX
Specs, VRAM requirements and download trends — updated 24 October 2026.
sentence-transformers · A · Open weights
Params
20 M
Context
512
30d
193.4 M
apache-2.0 · commercial OK
onnx-community · B · Open weights
Params
300 M
Context
2,048
30d
537 K
gemma licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | all-MiniLM-L6-v2 | embeddinggemma-300m-ONNX |
|---|---|---|
| Parameters | 20 M | 300 M |
| Architecture | BertModel | Gemma3TextModel |
| Context length | 512 | 2,048 |
| Licence | apache-2.0 | gemma |
| Commercial use | Allowed | Conditional |
| Languages | 1 | — |
| Downloads 30d | 193,424,443 | 537,487 |
| Downloads all time | 4.1 B | 1.6 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2025-08-22 |
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
259.7 M410 K
all-MiniLM-L6-v2
embeddinggemma-300m-ONNX
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
all-MiniLM-L6-v2 · fp16
0.6 GB / 24 GB