Inkling-Small Released: 276B Parameter MoE Model
simonguozirui · x · 2026-07-31
Thinkymachines has released Inkling-Small, a Mixture-of-Experts (MoE) model with 276B total parameters and 12B active parameters. It features a 1M token context window, variable thinking effort, and native image and audio understanding.
The developers claim it achieves performance comparable to the larger Inkling model at a quarter of the size, with full weights openly available. Users can fine-tune it on Tinker or interact with it in the Tinker Playground. Modal has announced Day 0 support, noting that its NVFP4 checkpoint fits on a single NVIDIA B300 GPU.
Related event: Thinking Machines Releases Inkling-Small Open-Source Model(23 posts)→
More from Models
- Inkling-Small: New MoE Model for Image/Audio-to-Text Trends on Hugging Face — thinkingmachines · 2026-07-31
- Gemini Ranks 3rd in HyperWrite Usage, Closing Gap on Claude — josh_bickett · 2026-07-31
- 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
- GPT-5.6 Hits 13% in AI Space Race Test, Beating Open-Source Kimi K3 — scaling01 · 2026-07-31