---
format: "aidr-story-markdown/v1"
id: "2bd63232151d599d96feb3ebe41f8375b336d1e0230418829da3478d269d1b60"
canonical_url: "https://aidr.today/2bd63232?lang=en"
title: "OpenArch – PyTorch implementations of modern LLM architectures"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-14T07:55:19.000Z"
category: "Models"
topics: ["llm","open-source","pytorch","llama","qwen","deepseek"]
source_urls: ["https://github.com/anuj0456/OpenArch","https://news.ycombinator.com/item?id=49693384"]
summary: "PyTorch implementations of modern open-source LLM architectures (Llama, Qwen, DeepSeek, Gemma, GPT-OSS, Kimi, and more) — written from scratch for readability and learning, based on Sebastian Rasch..."
---

# OpenArch – PyTorch implementations of modern LLM architectures

> [Open the canonical story](<https://aidr.today/2bd63232?lang=en>)

**Published:** 2026-09-14T07:55:19.000Z
**Category:** Models
**Topics:** llm, open\-source, pytorch, llama, qwen, deepseek

## Summary

PyTorch implementations of modern open\-source LLM architectures \(Llama, Qwen, DeepSeek, Gemma, GPT\-OSS, Kimi, and more\) — written from scratch for readability and learning, based on Sebastian Rasch\.\.\.

## Sources

- [Story source](<https://github.com/anuj0456/OpenArch>)
- [Discussion](<https://news.ycombinator.com/item?id=49693384>)