Models that fit in comercial hardware and are enterprise level efficient.
-
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
Any-to-Any • 33B • Updated • 322k • 422 -
Qwen/Qwen3.6-35B-A3B
Image-Text-to-Text • 36B • Updated • 3.93M • • 2.8k -
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 26B • Updated • 8.98M • • 1.49k -
LiquidAI/LFM2.5-8B-A1B
Text Generation • 8B • Updated • 82.5k • 762