Inkling-Small: The Lightweight Inkling

Alongside the 975B flagship, Thinking Machines previewed Inkling-Small — 12B active parameters, same training recipe, dramatically lower hardware requirements.

What We Know About Inkling-Small

Thinking Machines previewed Inkling-Small alongside the flagship Inkling AI launch on July 15, 2026. The official description is short but dense: a lighter-weight model with 12B active parameters, trained with a similar recipe to its 975B sibling, achieving strong performance with even lower cost and latency.

That framing matters. "Similar recipe" implies the same 45-trillion-token multimodal pretraining approach and likely the same controllable-thinking-effort design — compressed into a size class that runs on hardware people actually own. Where the full Inkling AI needs at minimum 290GB of RAM+VRAM even at 1-bit quantization, a 12B-active model quantized to 4-bit could plausibly fit in under 16GB.

For most developers watching this launch, Inkling-Small is arguably the more consequential release: the flagship demonstrates the recipe, but Small is the one that will end up on laptops, in fine-tuned vertical products, and inside agents that need cheap, fast multimodal reasoning.

Inkling vs Inkling-Small at a Glance

Spec Inkling AI Inkling-Small
Active parameters 41B 12B
Total parameters 975B Not disclosed
Status Released (weights on Hugging Face) Preview announced
Training recipe 45T multimodal tokens "Similar recipe" (per Thinking Machines)
Realistic hardware 290GB+ RAM/VRAM minimum Likely single high-end GPU / Apple Silicon
Target use Customization base for orgs Low-cost, low-latency deployment

We will update this page as Thinking Machines publishes Inkling-Small's full model card.

Inkling-Small FAQ

When will Inkling-Small be released?
Thinking Machines shared Inkling-Small as a preview alongside Inkling's July 15, 2026 launch, without a firm release date. It says the model is trained with a similar recipe and will be part of the growing Inkling family.
How big is Inkling-Small?
Thinking Machines describes it as a lighter-weight model with 12B active parameters — total parameter count hasn't been disclosed. That active size puts single-node and even high-end consumer inference in reach.
Will Inkling-Small be multimodal too?
Trained 'with a similar recipe' suggests yes, but Thinking Machines hasn't confirmed the full modality set for the preview. We will update as details land.
What hardware will Inkling-Small need?
With 12B active parameters, quantized variants should run on a single high-VRAM consumer GPU or Apple Silicon Mac — a completely different class from the 290GB minimum of its big sibling.