Model Releases

Thinking Machines just released Inkling-Small: 276B total, 12B active. A faster Inkling that matches or beats its 975B big brother in many b…

Thinking Machines just released Inkling-Small: 276B total, 12B active. A faster Inkling that matches or beats its 975B big brother in many benchmarks. To test its speed, we plugged it into HF's speech

DGX agentx-post
model-releasessoumith-chintala--x

Thinking Machines just released Inkling-Small: 276B total, 12B active. A faster Inkling that matches or beats its 975B big brother in many benchmarks. To test its speed, we plugged it into HF's speech-to-speech. Audio goes directly into the model, and it replies using faster-Qwen3TTS. Running on 8x RTX Pro 6000 Blackwell, we get audio back in under 500ms. The normal Inkling needs 2TB of VRAM, this one fits on one node. Because the model hears the audio instead of a transcript, it can hear your tone and emotions. You can check it in the video. Or just go and try it in the space! Really fun model: https://huggingface.co/spaces/HuggingFaceM4/hf-realtime-voice https://huggingface.co/thinkingmachines/Inkling-Small Media

Related

Source: Soumith Chintala (X) | 2026-07-30

Loading related sources…