Article complete

Thinking Machines Shrinks Inkling to 12B Active Parameters Without Giving Up Performance

The open-weight model supports text, image and audio reasoning with a context window of up to one million tokens.

A woman in a silk shirt poses thoughtfully against a vibrant purple background with a circular yellow halo effect.

Key takeaways

  • Thinking Machines Lab has introduced Inkling-Small, a model with significantly fewer active parameters yet comparable performance to its flagship model.
  • Inkling-Small features 276 billion total parameters, with only 12 billion active parameters, supporting a context window of up to one million tokens.
  • The model is designed for native reasoning across text, images, and audio, and is available for fine-tuning on the Tinker platform.
  • Inkling-Small's development involved enhancements in pre-training data and training techniques, utilising on-policy distillation for improved performance.
  • This release follows the launch of the original Inkling model, which has a much larger parameter count and supports multimodal inputs.

Takeaways drafted with AI from the article text.

The model has 276 billion total parameters with 12 billion active parameters, compared with Inkling’s 41 billion active parameters, and supports a context window of up to one million tokens.

The company said Inkling-Small is available immediately through Tinker with a limited-time discount alongside the original Inkling model. “It’s a capable and efficient model, and an important stepping stone for us as we continue our work,” it said.

Inkling-Small was trained on NVIDIA GB300 NVL72 systems and supports native reasoning across text, images and audio. It is being released with full model weights and is also available for fine-tuning on the company’s Tinker platform and for multimodal chat through Tinker Playground.

“As we build our model family, we are always iterating on our approach,” the company said. It added that Inkling-Small benefited from changes to its pre-training data mix and training recipe, and that an earlier preview checkpoint was post-trained using on-policy distillation with Inkling as the teacher before further reinforcement learning for agentic coding.

This is the second model in the Inkling series. A few days ago, the company launched Inkling, a mixture-of-experts (MoE) transformer with 975 billion total parameters and 41 billion active parameters. The multimodal model supports a context window of up to one million tokens and was pre-trained on 45 trillion tokens spanning text, images, audio, and video.

According to Thinking Machines Lab, Inkling-Small matches or surpasses Inkling on several reasoning and coding benchmarks despite its smaller active parameter count. 

The company said the model scored 31.6% on Humanity’s Last Exam, ahead of Inkling’s 29.7%, and exceeded 80% on SWE-bench Verified. It also said Inkling-Small offers a better performance-to-compute trade-off across several reasoning and agentic tasks.

The model also retains multimodal capabilities. Thinking Machines Lab said Inkling-Small uses the same encoder-free architecture as Inkling, allowing it to process audio, images and text together. The company said it improved the model’s ability to use Python for visual tasks, including document and chart analysis, while maintaining performance across visual reasoning, speech understanding and longer-form audio reasoning.










Published

Spotted an error? Tell our editors. Read our editorial standards and corrections.

More in this story

NVIDIA · 5 stories
  1. HCL Launches VisionX 2.0 AI Edge Platform With NVIDIA
  2. OpenAI Unveils 16MB, 10-Min Model Training Challenge on NVIDIA H100 GPUs
  3. You are here: Thinking Machines Shrinks Inkling to 12B Active Parameters Without Giving Up Performance
  4. Meta Releases 816B-Parameter Open-Weight Model With 1M Context Window
  5. NVIDIA Launches Open-Weight Transcription Model for 40 Languages
About the author

Tech Journalist

Siddharth is a media graduate who loves to explore tech through journalism and putting forward ideas worth pondering about in the era of artificial intelligence.

All stories
Belamy · Daily

The day’s AI news, before your first meeting.