multilingual-e5-base vs embeddinggemma-300m

Specs, VRAM requirements and download trends — updated 21 September 2026.

intfloat · A
Params
280 M
Context
512
30d
7.6 M
mit · commercial OK
google · B
Params
300 M
Context
30d
2.7 M
gemma licence · conditional

Specification comparison

Differences are highlighted; identical values are muted.

Specification multilingual-e5-base embeddinggemma-300m
Parameters 280 M 300 M
Architecture XLMRobertaModel Gemma3TextModel
Context length 512
Licence mit gemma
Commercial use Allowed Conditional
Languages 94
Downloads 30d 7,570,279 2,674,650
Downloads all time 65.4 M 18.6 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No Yes — accept licence
First seen on the Hub 2023-05-19 2025-07-17

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

7.6 M1.9 M
multilingual-e5-base embeddinggemma-300m

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

multilingual-e5-base · fp16 1.8 GB / 24 GB
✅ Runs comfortably
embeddinggemma-300m · fp16 1.9 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons