← Local AI Release Board

AlmawaveLabs/Velvet2-3B-Vision

just landed · new, unvettedmodel

New, unvetted: created or first seen in the last few days, not from a trusted org and not past the signal threshold yet.

Velvet2 is the new generation of models developed by Almawave Labs, designed to provide a unified platform for multilingual, multimodal, and enterprise AI applications. 4.3B params. License: apache-2.0. Vendor-reported: "Velvet2 is the new generation of state of the art models developed by Almawave Labs, designed to provide a unified platform for multilingual, multimodal, and enterprise AI applications." Vendor-reported: "Velvet2-3B-Vision outperforms both Salamandra-VL-7B and Villanova-2B-VL-2603 on nearly all shared benchmarks while using fewer parameters than Salamandra-VL-7B."

Org
AlmawaveLabs
Released
2026-10-14
Status
just landed · new, unvetted
License
apache-2.0 (permissive)
Parameters
4.3B
Task
image-text-to-text · vision
Signal
8 HF likes · 55 downloads
Weights
gated

Runs on

mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.

Links

First published here 2026-10-14 · updated 2026-10-30 · markdown · JSON