Repo RadarNewsletter

Trending/LLM & models

LLM & models

divagr18/qwenputer

A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.

★ 150Week rank 78 · star gain starts at the next snapshot

View on GitHub

From the README

Qwenputer model: Hugging Face · ModelScope Filesystem model: Hugging Face · ModelScope **Qwenputer is a new kind of experimental model: Qwen3.5-4B with a 32-bit RISC-V CPU compiled and inserted directly into its weights.** It isn't a plugin, a tool or a sandbox. The CPU is 11 transformer layers in front of Qwen's own, and none of their weights are learned: a compiler computes every one.

Setup prompt

Paste this into Cursor or Claude Code. It only includes install lines found in the README, and it asks the agent to review the code first.

Set up the GitHub repository divagr18/qwenputer (A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.).
Repository: https://github.com/divagr18/qwenputer

Official install commands found in the README:
git clone https://github.com/divagr18/qwenputer && cd qwenputer/experimental/riscv && uv sync --extra hf
uv run python -m chipformer.rv.chat qwenputer-rv --firmware tests/data/rv/calc-bridge.elf \
git clone https://github.com/divagr18/qwenputer && cd qwenputer
uv sync --extra hf
uv run python -m chipformer.q35.demo qwenputer-4b                   # Qwen uses its tool-call syntax
uv run python -m chipformer.q35.demo qwenputer-4b --inline --nudge  # plain inline arithmetic

Clone the repository and follow those steps. Do not invent package names or extra install commands.
Review the code before running anything.

Buzz by window

Same mentions, three half-lives. This is not a star history. Star gain appears after a second daily snapshot.

  • Today1.02
  • Week1.77
  • Month1.93

Spotted on

Related

Report a problem or request removal