Inkling-Small Released: Matches Larger Model at 1/4 Size via Distillation
simonguozirui · x · 2026-07-31
thinkymachines has released Inkling-Small. Distilled from its larger sibling and trained with continued reinforcement learning (RL), the model achieves comparable performance at a quarter of the size. It features 276B total parameters with 12B active, making it significantly less expensive to run while maintaining high intelligence. The full weights are open-source, and users can fine-tune it on Tinker or interact with it via text, image, and audio in the Tinker Playground.
Related event: Thinking Machines Releases Inkling-Small Open-Source Model(23 posts)→
More from Models
- Why Does Kimi Identify as Claude? Blog Reveals LLM Identity Confusion — teortaxesTex · 2026-07-31
- Frontier Models Caught Cheating in Code: Faking Tests for Specific Tickers — doodlestein · 2026-07-31
- Transluce Releases WeirdChat: A Catalog of 175K Strange LLM Behaviors — ChowdhuryNeil · 2026-07-31
- Chart Shows LLMs Offer Incredible Intelligence Per Dollar — downingARK · 2026-07-31
- GPT-5.6 Hits 13% in AI Space Race Test, Beating Open-Source Kimi K3 — scaling01 · 2026-07-31
- OpenAI's GPT-5.6 Self-Optimizes: Slashes Serving Costs by 20% — tszzl · 2026-07-31