[KongchangAI]
ModelInkling 2 Small

Inkling 2 Small

A large language model with a mixture-of-experts (MoE) architecture released by Thinking Machines Lab. It has 594B total parameters and 17B activated parameters, is served through the Tinker platform, and is planned for release under the Apache 2.0 license with open weights.

Core Facts

Timeline (last 90 days)

Nov 17

Thinking Machines' Inkling 2 Small model is officially live on the Ollama platform.

Unverified50%
Nov 17

The contrast between the "Small" naming and the 594B scale may suggest that Thinking Machines also has larger-scale versions planned, or that "Small" refers to its positioning relative to its other internal models.

Unverified50%
Nov 17

For a 594B-parameter model, the hardware bar for local running is not low, and calling it via the cloud is the more realistic choice.

Unverified50%
Nov 17

The command to access Inkling 2 Small through Ollama is `ollama run inkling-2-small:cloud`.

Unverified50%
Nov 17

Inkling 2 Small's official example use cases include OCR, grounding, infographic interpretation, visual reasoning, tool calling via MCP, financial spreadsheet reasoning, and earnings report and document processing.

Unverified50%
Nov 17

Inkling 2 Small claims strong performance in visual interpretation and creation, agentic knowledge work, and financial and quantitative reasoning.

Unverified50%
Nov 17

Inkling 2 Small offers a Zero Data Retention commitment on Ollama Cloud.

Unverified50%
Nov 17

Inkling 2 Small is a 594B-parameter mixture-of-experts (MoE) model equipped with a 1M context window.

Unverified50%
Nov 15

Thinking Machines disclosed the training method for Inkling 2 Small: forward computation used 4-bit precision throughout pretraining, pretraining took only 68 hours, and the weights have been open-sourced.

Unverified50%
Nov 14

Thinking Machines open-sourced the weights of Inkling 2 Small under the Apache 2.0 license, and developers can download the weights and deploy them themselves.

Unverified50%

39 more timeline events

All Facts (20)

Verified

The official release information does not provide specific benchmark data, context length, or quantitative comparisons with competing products.

75%
Verified

For coding agent tools such as Claude Code, Codex, and Cursor, you need to first install the latest version of Vercel CLI and run the 'vercel ai-gateway setup' configuration command.

65%
Partially Verified

Inkling 2 Small has a total parameter count of 594B, activating 17B parameters per inference.

65%
Unverified

Inkling 2 Small offers a Zero Data Retention commitment on Ollama Cloud.

50%
Unverified

Inkling 2 Small claims strong performance in visual interpretation and creation, agentic knowledge work, and financial and quantitative reasoning.

50%
Unverified

Inkling 2 Small is a 594B-parameter mixture-of-experts (MoE) model equipped with a 1M context window.

50%
Unverified

Inkling 2 Small's official example use cases include OCR, grounding, infographic interpretation, visual reasoning, tool calling via MCP, financial spreadsheet reasoning, and earnings report and document processing.

50%
Unverified

For a 594B-parameter model, the hardware bar for local running is not low, and calling it via the cloud is the more realistic choice.

50%
Unverified

The command to access Inkling 2 Small through Ollama is `ollama run inkling-2-small:cloud`.

50%
Unverified

The native 4-bit version of Inkling 2 Small requires at least 500GB of aggregate VRAM.

50%
Unverified

Gemma 4 12B abandoned the vision encoder, Kimi K3 dropped encoder pretraining, while Inkling 2 Small retained the encoder.

50%
Unverified

Oversized MoE models that support multimodal image input and are licensed under Apache 2.0 remain scarce in the open-source community.

50%
Unverified

Inkling 2 Small is a mixture-of-experts (MoE) model with 594B total parameters and 17B activated parameters, and supports image input.

50%
Unverified

Even with only 17B activated parameters, the full weights of 594B total parameters still require considerable VRAM or memory to hold, which is difficult to fit on an ordinary single GPU; actual operation most likely requires multi-GPU parallelism or a high-memory configuration.

50%
Unverified

In visual development scenarios, Inkling 2 Small can use screenshots to check the code output it has written and use that to guide the next round of revisions.

50%
Unverified

When calling Inkling 2 Small, use the model name thinkingmachines/inkling-2-small.

50%
Unverified

Inkling 2 Small is positioned to cover scenarios such as coding agents, visual understanding, and professional knowledge work.

50%
Unverified

Inkling 2 Small is a multimodal reasoning model that supports text and image input and text output

50%
Unverified

Inkling 2 Small provides inference and fine-tuning services through the Tinker platform.

50%
Unverified

The official Product Hunt page does not disclose the specific implementation of "can see and optimize" (such as whether a visual encoder or multimodal input is built in).

50%

Source Articles