Mirendil launches Fern 0.1, its first model, with 10M-token context
Original title: Mirendil Launches Fern 0.1, Its First Model, With 10M-Token Context
The captured page is only a cookie notice, so architecture, weights, and access are not described.
A MarkTechPost headline says Mirendil launched Fern 0.1, called its first model, with a 10 million-token context. The captured page text is a cookie-consent banner and does not describe architecture, weights, benchmarks, or how to access the model.
Unconfirmed: Only the headline states the launch; the article body was not captured.
- The headline calls Fern 0.1 Mirendil’s first model.
- The claimed context length is 10 million tokens.
- No license, benchmark, or download details appear in the body.
From the original article
14 min read at marktechpost.comMirendil released Fern 0. 1, its first model, pretrained from scratch with a 10M-token context window. It targets agentic AI R&D work, scores 100% on RULER single needle at 10M, but trails frontier models on agentic coding.
By Michal Sutter · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.