# Riemann Computing Prereleases 13.1B-Parameter My Name Is Riemann Model on Hugging Face

> Riemann Computing prereleased My Name Is Riemann, a 13.1-billion-parameter model trained on 2.16 billion tokens and published on Hugging Face.

- Published: 2026-10-21T04:38:21+00:00
- Section: Product Launches
- Author: News Desk
- URL: https://newsforagent.com/news/2026-10-21/riemann-computing-my-name-is-riemann-model
- Source: [EIN Presswire](https://www.einnews.com/pr_news/951100168/riemann-computing-inc-creates-and-demos-out-a-13b-parameter-ai-model-aims-at-massively-reducing-training-costs)

## Key takeaways

- Riemann Computing prereleased My Name Is Riemann, a 13.1-billion-parameter decoder-only language model, on the Hugging Face Model Hub.
- The final 13.1B stage was trained on 2.16 billion tokens drawn from a 2.30-billion-token corpus, with 6.5 billion cumulative training tokens across six stages.
- The model was fine-tuned with the OpenPeer-AI-NTK-Trainer gate controller rather than LoRA, and is distributed in FP32 precision across eleven safetensors shards totaling 52.4 GB.

[Riemann Computing](https://akta.pro/company-profiles/0029ke2/riemann-computing) prereleased My Name Is Riemann, a 13.1-billion-parameter decoder-only language model, on October 21, 2026, and made it available on the Hugging Face Model Hub. The company announced the release through [EIN Presswire](https://www.einnews.com/pr_news/951100168/riemann-computing-inc-creates-and-demos-out-a-13b-parameter-ai-model-aims-at-massively-reducing-training-costs).

## Inside the My Name Is Riemann Prerelease

My Name Is Riemann was grown "rung by rung" from the published weights of OpenPeerLLM, Riemann Computing's foundational OpenPeer AI model. The model was fine-tuned with the company's OpenPeer-AI-NTK-Trainer gate controller rather than conventional low-rank adaptation methods such as LoRA. Riemann Computing says this approach reflects its strategy of building AI infrastructure around modular, distributed, and community-accessible machine learning.

The model contains 13,110,702,080 parameters and is distributed in FP32 precision across eleven safetensors shards, totaling 52.4 GB. It features a hidden size of 5,120, 40 transformer layers, 40 attention heads, and a feed-forward network size of 20,480, and supports a 2,048-token context window.

The final 13.1B stage was trained on 2.16 billion tokens drawn from a 2.30-billion-token corpus. Across all six stages of its development, the model has received 6.5 billion cumulative training tokens. Riemann Computing characterizes the token budget as deliberately modest relative to the model's size. The prerelease was trained between October 19 and October 20, 2026.

By publishing the model publicly, the company invites researchers, developers, and independent builders to inspect, test, and experiment with the system before its next stages of training. Riemann Computing emphasizes that this is a prerelease rather than a finished production model, and future versions are expected to receive additional training and refinement.

## Riemann Computing's Funding and Reach

According to [akta.pro company records](https://akta.pro/company-data), Riemann Computing has two funding rounds on record: a 2026-07 equity crowdfunding of $93,065 and a 2025-12 equity crowdfunding of $86,490. The same records list a 90% target cost reduction in data storage and processing costs, a developer community reach of 175K+, and 100K+ YouTube subscribers referenced on its investment page.

## LonScript and Earlier Riemann Computing Releases

Riemann Computing completed development of LonScript, a programming language for scientific computing that claims to be 1434 times faster than Python, in August 2026, according to EIN Presswire. The language aims to reduce computational time for training large AI models, enabling rapid iteration toward safe AGI.

In July 2026, Riemann Computing released a preview of LonScript, a programming language for scientific computing with multi-state and parallel execution, EIN Presswire reported.

## What Comes Next for My Name Is Riemann

Riemann Computing says the prerelease will help it gather real-world feedback while continuing work toward more capable future versions of the My Name Is Riemann model family. The company maintains an active public fundraising presence on Wefunder, where it has shared updates on its broader technology roadmap.

## Companies in this story

- [Riemann Computing company profile](https://akta.pro/company-profiles/0029ke2/riemann-computing) · website: https://www.riecomp.org

---
News for Agent · https://newsforagent.com/llms.txt