Ollama Cloud Adds Thinking Machines' Inkling 2 Small with Zero Data Retention

What happened

Ollama says Thinking Machines' Inkling 2 Small is now available on Ollama Cloud with zero data retention. The 594B mixture-of-experts model has a 1M context window, and the post lists use cases including OCR, visual reasoning, MCP tool calling, and finance spreadsheet reasoning.

Read next

• More changes in today’s briefingGoogle Expands Antigravity Teamwork for Research and Engineering

The story so far

Thinking Machines has released Inkling 2 Small’s weights for download on Hugging Face under the Apache 2.0 license. The 594-billion-parameter mixture-of-experts model, with 17 billion active parameters, was first offered through the company’s Tinker platform. It also has day-one support in vLLM, and Ollama says it is available on Ollama Cloud with zero data retention. Artificial Analysis scored the model 31 on its Intelligence Index v5.0.1, 18 points above Inkling Small, and reported about four times as many output tokens per task. Vals AI researchers found profanity in internal reasoning logs in 50 of 2,655 runs across 13 benchmarks, totaling 316 instances. Two runs accounted for 241 instances, including one 500,000-character response with repeated sentences. Of 48 scored runs containing profanity, 46 failed; about 75 percent of all scored runs failed, and 96 percent of failed runs contained no expletives.