all-MiniLM-L6-v2 vs e5-mistral-7b-instruct

Specs, VRAM requirements and download trends — updated 7 September 2026.

Xenova · A
Params
20 M
Context
512
30d
3.0 M
apache-2.0 · commercial OK
intfloat · B
Params
7.1 B
Context
32,768
30d
424 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification all-MiniLM-L6-v2 e5-mistral-7b-instruct
Parameters 20 M 7.1 B
Architecture BertModel MistralModel
Context length 512 32,768
Licence apache-2.0 mit
Commercial use Allowed Allowed
Languages 1
Downloads 30d 3,020,634 424,422
Downloads all time 28.1 M 7.8 M
Quantizations on the Hub SAFETENSORS
Gated No No
First seen on the Hub 2023-05-02 2023-12-20

Download trend

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

3.0 M420 K
all-MiniLM-L6-v2 e5-mistral-7b-instruct

VRAM side by side

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

e5-mistral-7b-instruct · fp16 17.2 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons