LecturaInvestigaciónRadarMarco de inversión
Iniciar sesión / Registrarse
← Volver a la lectura
NoticiasTema · Qwenputer项目Resumen rápido1 min de lecturaEditorial de DisconfirmAI

AI Engineer Compiles RISC-V Processor Directly Into LLM Weights to Run DOOM Internally

Developer Divyansh Agrawal embedded a 32-bit RISC-V CPU into Qwen 3.5 4B weights, enabling internal execution of C code and DOOM without external tools.

2026-11-02 21:30 GMT+8

AI engineer Divyansh Agrawal has released an experimental project called Qwenputer, successfully compiling and embedding a 32-bit RISC-V CPU directly into the weights of the Qwen 3.5 4B large language model. This innovation allows the model to use its own weights as memory (RAM) to execute processor arithmetic operations, C, and MicroPython code internally, without relying on any external runtime or tool calls, and even run the classic game DOOM at a very slow speed.

Unlike traditional model training, this built-in 'CPU' was not learned through machine learning but computed entirely by a compiler across 11 Transformer layers placed before Qwen's original layers. Agrawal claims the built-in CPU passes official riscv-tests, matches qemu programs, and has run 18 million instructions free-running without a single error. This design overcomes the common arithmetic weaknesses of LLMs by providing exact calculation capabilities. Additionally, the project uses DeltaNet state to provide the model with a filesystem supporting up to 512 files with persistent storage.

Due to expanded resource usage, Qwenputer is nearly twice the size of the underlying Qwen 3.5 4B model, reaching almost 19GB, thus requiring a workstation with at least 24GB of VRAM for testing. The project remains highly experimental, primarily exploring technical possibilities rather than solving specific production problems, though its MIT-licensed code is now available on GitHub.

Iniciar sesión / Registrarse
LecturaInvestigaciónRadarMarco de inversión

Fuentes

  • tomshardware.comTom's Hardware↗
Tema

Qwenputer项目

AI工程师Divyansh Agrawal发布实验性模型“Qwenputer”,将32位RISC-V CPU直接编译进Qwen 3.5 4B大模型的权重中。该模型利用Gated DeltaNet状态作为RAM,无需外部工具即可在模型内部执行…

5 pasos1 piezasActualizado 2026-11-03 01:02

Cómo llegó hasta aquí

  1. 2026-10-22开发者Divyansh Agrawal发布博客文章,正式介绍Qwenputer项目及其技术原理。divagr.com ↗
  2. 2026-10-28Agrawal在社交媒体上展示Qwenputer运行C代码和MicroPython的能力,引发关注。x.com ↗
  3. 2026-10-29Agrawal演示Qwenputer在内置RISC-V CPU上运行《DOOM》E1M1关卡。tomshardware.com ↗

Lo que aún está pendiente

  • Qwenputer在更复杂的生产环境中的实际延迟和资源消耗优化路径是什么?
  • 这种“编译权重”方法是否会被其他主流LLM厂商采纳以解决幻觉或计算错误问题?
  • 文件系统持久化状态在多轮对话中的稳定性和安全性如何验证?
Leer el tema completo →
Continuar investigando →