roberta-base-go_emotions vs ms-marco-MiniLM-L-6-v2

Specs, VRAM requirements and download trends — updated 24 October 2026.

SamLowe · A · Open weights
Params
120 M
Context
512
30d
4.6 M
mit · commercial OK
Xenova · B · Open weights
Params
—
Context
512
30d
710 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification roberta-base-go_emotions ms-marco-MiniLM-L-6-v2
Parameters 120 M —
Architecture RobertaForSequenceClassification BertForSequenceClassification
Context length 512 512
Licence mit —
Commercial use Allowed Unknown
Languages 1 —
Downloads 30d 4,606,140 710,372
Downloads all time 104.2 M 3.0 M
Quantizations on the Hub SAFETENSORS —
Gated No No
First seen on the Hub 2022-09-15 2024-01-04

Download trend

Daily snapshots, last 89 days (28 Jul – 24 Oct)

4.7 M250 K
roberta-base-go_emotions ms-marco-MiniLM-L-6-v2 A overtook B on 22 Sep

VRAM side by side

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

roberta-base-go_emotions · fp16 1.1 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons