Holotron-12B - High Throughput Computer Use Agent

Hugging Face · 6 months ago · 36

H Company released Holotron-12B, a 12-billion-parameter multimodal model designed to serve as a policy model for computer-use agents that perceive and act in interactive environments. On the WebVoyager benchmark with 100 concurrent workers, Holotron-12B achieved 8.9k tokens per second throughput on a single H100 GPU, more than 2 times higher than Holo2-8B's 5.1k tokens per second. The model's hybrid state-space and attention architecture enables enterprises to deploy computer-use agents at scale with reduced memory requirements and improved batch processing efficiency.