![[AINews] Thinking Machines' Native Interaction Models - TML-Interaction-Small 276B-A12B - advances SOTA Realtime Voice and kills standard VAD](https://substackcdn.com/image/fetch/$s_!LR03!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F02190942-3f50-4067-ae03-97c6b504b3a3_1490x1592.png)
[AINews] Thinking Machines' Native Interaction Models - TML-Interaction-Small 276B-A12B - Advances SOTA Realtime Voice and Kills Standard VAD
Latent Space2369 字 (约 10 分钟)
90
Thinking Machines released TML-Interaction-Small 276B-A12B, a 276-billion-parameter MoE model with only 12 billion active parameters, achieving sub-200ms end-to-end latency, surpassing GPT-4o and Gemini 3.1-Flash in real-time voice interaction, time-aligned microturns, and visual proactivity, effectively eliminating standard VAD.
入选理由：TML-Interaction-Small为276B参数MoE模型，仅12B激活参数，实现<200ms端到端延迟。
FeaturedArticle#AI#Realtime Voice#MoE#Multimodal#Model Architecture中文