X · @soumithchintala
· X / Twitter
RT Andi Marafioti: Thinking Machines just released Inkling-Small: 276B total, 12B active. A faster Inkling that matches or beats its 975B big brother …
RT Andi MarafiotiThinking 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