Inkling-Small Launches: 276B Params, 12B Active at One-Fifth the Cost
togethercompute · x · 2026-07-31
Thinking Machines Lab has released Inkling-Small, a new open-weight multimodal model now available on Together AI.
Built on a Mixture-of-Experts (MoE) architecture, the model has 276B total parameters with only 12B active per token. It natively reasons across text, image, and audio, supporting a context window of up to 1M tokens. The model is reported to match the performance of the larger Inkling model on Terminal-Bench 2.1 at roughly one-fifth of the cost, optimized for coding, agents, and general multimodal workloads.
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