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: Inkling-Small: 276B params, 12B active, open-source tops ARC(48 posts)→
More from Models
- Reflection's Beam lands on Hugging Face: 501B MoE, 1M context, Apache 2.0 open weights — tomaarsen · 2026-10-16
- Reflection launches Beam 1.0, its first open-weight model built for coding, reasoning and agentic tasks — tomaarsen · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite — airesearch12 · 2026-10-16
- LMArena launches Agent Arena and Code Arena leaderboards for model comparison — arena · 2026-10-16
- Third-party tests find NVIDIA Nemotron-3.5 Bolt underperforms nano on pandas/numpy and decision-making tasks — norenEnmotalen · 2026-10-16