Inkling-Small Released: Beats Larger Sibling at 1/4 the Size
simonguozirui · x · 2026-07-31
Inkling-Small has been officially released, featuring 276B total parameters with only 12B active.
At a quarter of the size of the larger Inkling model, it achieves comparable or superior performance on many benchmarks. It is particularly strong in agentic tasks and reasoning, outperforming strong peers in its class like DeepSeek V4 Flash.
The full weights are now available. Users can fine-tune the model on Tinker or interact with it via text, image, and audio on the Tinker Playground. It is also compact enough to run efficiently on a single DGX Spark.
Related event: Inkling-Small: 276B params, 12B active, open-source tops ARC(48 posts)→
More from Models
- Google restricts Gemini Pro access for Google Plus subscribers, matching free tier — EmergencyLess8861 · 2026-10-16
- Meta releases Muse Spark Open, trained with vLLM-powered RL inference from day one — colinmcnamara · 2026-10-16
- Meta open-sources Muse Spark: runs on two Mac Studios, license bans passing output off as human-written — mawcopolow · 2026-10-16
- Golden Gate Claude explainer resurfaces: interpretability premise still holds — HarperSCarroll · 2026-10-16
- Hugging Face livestreams release of a new open-weight model — huggingface · 2026-10-16
- Step 5 Preview hits #2 on OpenRouter weekly leaderboard with 19.5T tokens in one week — StepFun_ai · 2026-10-16