All models

COMPARE

Put models side by side.

What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.

Propertybiplov/emo-en-lora-proper
SummaryEmotion · lora (English). Which emotion does the writer express? Fine-tuned from aac6fef/laya-mlx.
Decideschoice
Architecturelaya
Fine-tuned fromaac6fef/laya-mlx
Licenseapache-2.0
Decision accuracy88.2%
Calibration error0.022
Valid action rate—
Median latency55 ms
p95 latency61.5 ms
Evaluation suiteEmotion (6 labels)
Latest version0.1.0
Variantsencoder, tokenizer
Size of latest version807.0 MB
Files7
Downloads0
Stars0
Tagsmlx
UpdatedSep 24, 2026