Inkling-Small Weights Released: 276B Total Params with 12B Active
clarejtbirch · x · 2026-07-31
Thinky Machines has released the full weights for Inkling-Small. Utilizing a Mixture-of-Experts (MoE) architecture, the model has 276B total parameters with only 12B active during inference. The developers claim it achieves performance comparable to the larger Inkling model.
Users can now fine-tune the model on the Tinker platform or interact with it via text, image, and audio in the Tinker Playground.
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