LMSYS Releases Inkling-small: 12B Active Parameters Lowers Multimodal RL Barrier

simonguozirui · x · 2026-07-31

LMSYS has released the new MoE model Inkling-small. With 276B total parameters but only 12B active, it is considered a sweet spot for multimodal Reinforcement Learning (RL).

Performance & Inference: Using the SGLang framework, the model achieves 648 tok/s on 8x B200 GPUs. Its capability matches the larger version and even wins on some benchmarks.

Industry Significance: The 12B active parameter count means small teams can actually run multimodal RL, not just read papers about it. Combined with the Miles framework, developers can directly turn multimodal data into real capability gains, marking an industry shift from 'collecting data hoping labs train on it' to 'customizing models autonomously'.

Related event: Thinking Machines Releases Inkling-Small: 276B MoE Open-Source Model(31 posts)→

Original post →

More from Models

Models channel →