Thinking Machines Launches 276B Inkling-Small for Ultra-Fast Speech-to-Speech
MaziyarPanahi · x · 2026-07-31
Thinking Machines released a new MoE model, Inkling-Small (276B total parameters, 12B active). It matches or beats its 975B predecessor in many benchmarks. In testing, it was plugged into HF's speech-to-speech pipeline where audio goes directly into the model and replies via faster-Qwen3TTS, achieving audio response latency of under 500ms on 8x RTX Pro 6000 Blackwell.
Related event: Inkling-Small: 276B params, 12B active, open-source tops ARC(48 posts)→
More from Models
- Why are sub-15B open models so rare now? Labs seem to have settled on 24-27B minimum — Hot_Example_4456 · 2026-10-16
- User spots model openly generating "ideal responses" to train other models — liminal_bardo · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16
- JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite — airesearch12 · 2026-10-16
- Team of 5 mulls dropping ChatGPT Pro for Business as OpenAI quota parity stays unclear — bettercallfool · 2026-10-16