aquif-ai/aquif-3.5-Max-1205

Text Generation • 42B • Updated about 20 hours ago • 127 • 8

Note new, thinking-only upgrade to the aquif-3.5-Max focused on coding and math performance.

aquif-ai/aquif-3.5-Max-42B-A3B

Text Generation • 42B • Updated 1 day ago • 70.2k • 78

Note our biggest model with 42.4B total, 3.3B active parameters and 1M context, made for hard coding and math tasks.

aquif-ai/aquif-3.5-Plus-30B-A3B

Text Generation • 31B • Updated 23 days ago • 580 • 30

Note medium-sized 30.5B total, 3.3B active model with 1M context for general tasks and coding on 16GB+ VRAM cards.

aquif-ai/aquif-3.5-Nano-1B

Text Generation • 2B • Updated 4 days ago • 141 • 6

Note small 1.7B model with 40K context for lightweight tasks and edge devices; outperforms aquif-3.5-3B and Ministral.