Understand this story
English text is being prepared.
AI-generated from public reports
Latest development · Report
Qwenputer embeds a RISC-V CPU in the Qwen3.5-4B weights and uses GDN state as memoryDevelopments
1 confirmed developments
- Source:Shao Meng
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 31
Shao MengSelected
Qwenputer embeds a RISC-V CPU in the Qwen3.5-4B weights and uses GDN state as memory
On Qwen3.5-4B, Qwenputer uses a compiler to write a 32-bit RISC-V CPU into about 11 layers of additional weights, and treats the model's built-in Gated DeltaNet state as addressable RAM, running C and MicroPython in the forward pass without calling an external runtime. In testing, the DeepMind arithmetic set reached about 97.5–100%, NUPA long integers improved from 48.6% for the base model to 100%, and about 230,000 CPU output positions showed zero mismatches against the reference machine. The costs are a checkpoint of about 18.8 GB, several decode tokens required per CPU instruction, and the need to drive it through RvChat rather than bare generate().
Simon Willison
Drew Breunig writes a NES emulator into the Qwen3.5-4B weights
Inspired by Divyansh Agrawal's qwenputer, Drew Breunig wrote a runnable NES 6502 CPU emulator into the weights of Qwen3.5-4B, and it can now (very slowly) run NES ROMs such as Super Mario Bros inside Qwen. In a Hacker News comment, he disclosed the prompts used when building the system with Opus 5.5, noting that Opus found and used the NES CPU consistency test suite that Christopher Pow published 15 years ago.
Oct 30
English text is being prepared.
Qwenputer Arrives: Packing the RISC-V CPU Instruction Set into a Model, AI Arithmetic No Longer Relies on External Tools
Developer Divyansh Agrawal released the experimental model Qwenputer on October 22. Built on Alibaba's Qwen3.5-4B, it implements a 32-bit RISC-V CPU and memory functions inside the model, enabling it to execute programs and perform precise calculations without calling external tools. In tests, large-integer multiplication accuracy rose from 55% to 97.5%, and the long-integer arithmetic benchmark NUPA reached 100%, compared with only 48.6% for the standard version. The cost is that the model size grows to about 18.8GB, each instruction requires generating multiple tokens and thus takes several seconds, and a dedicated driver is needed. The project has been open-sourced on Hugging Face and GitHub.
IT Home · AIRelated discussion
IT Home · AI joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Heat trend for this story
- Current
- 7
- Period peak
- 15 Oct 31 10:00
- 24-hour change
- -50%
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.