# Occamy-1.0 Puts a 35-Billion-Parameter Open Model Against Larger Agent Systems

The model is further trained from a post-trained Qwen3.6-35B-A3B checkpoint and targets the cost-per-episode problem that makes long agent workflows expensive.

- Published: 2026-09-14T06:22:55.303Z
- Canonical: https://polylog.news/ai/2026-09-14/occamy-1-0-puts-a-35-billion-parameter-open-model-against-la
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv](https://arxiv.org/abs/2609.11977)

A preprint posted on September 14 introduces Occamy-1.0, a 35-billion-parameter model aimed specifically at what its authors call co-work: agent workflows that combine information gathering, tool use, coding, and file manipulation across ma…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-14/occamy-1-0-puts-a-35-billion-parameter-open-model-against-la (subscription information: https://polylog.news/pricing).