---
format: "aidr-story-markdown/v1"
id: "820fdeda48b07bb8844e502423431da7fd2eeb55a6606794b4f30e2b4ddfd85c"
canonical_url: "https://aidr.today/820fdeda?lang=en"
title: "Marin's Mochi 535B Open Model Finishes Pretraining on 18T Tokens"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-05T22:38:53.000Z"
category: "Models"
topics: ["llm"]
source_urls: ["https://marketbrief.now/ai/marins-mochi-535b-open-model-finishes-pretraining-on-18t-tokens-cc592ac6","https://huggingnews.com/ai/marins-mochi-535b-open-model-finishes-pretraining-on-18t-tokens-cc592ac6"]
summary: "The Mochi 535B-A23B open source model has completed its pretraining phase after processing 18 trillion tokens and will now undergo long context training and supervised fine tuning before public release."
---

# Marin's Mochi 535B Open Model Finishes Pretraining on 18T Tokens

> [Open the canonical story](<https://aidr.today/820fdeda?lang=en>)

**Published:** 2026-11-05T22:38:53.000Z
**Category:** Models
**Topics:** llm

## Summary

The Mochi 535B\-A23B open source model has completed its pretraining phase after processing 18 trillion tokens and will now undergo long context training and supervised fine tuning before public release\.

## Sources

- [Story source](<https://marketbrief.now/ai/marins-mochi-535b-open-model-finishes-pretraining-on-18t-tokens-cc592ac6>)
- [Story source](<https://huggingnews.com/ai/marins-mochi-535b-open-model-finishes-pretraining-on-18t-tokens-cc592ac6>)