Researchers have developed Qwenputer, an experimental model that embeds a functional, deterministic RISC-V CPU directly within the weights of the Qwen 3.5-4B language model. This novel approach utilizes the model's own Gated DeltaNet attention layers as RAM, allowing it to perform arithmetic operations and execute code written in C and MicroPython without external tools. The CPU operates entirely within the model's forward passes, offering a unique method for in-model computation and storage. AI
IMPACT This research demonstrates novel methods for in-model computation and memory, potentially influencing future AI architectures.
RANK_REASON The cluster describes a novel research experiment integrating a CPU into an LLM's weights, not a commercial release or product launch.
Read on Mastodon — mastodon.social →
- Gated DeltaNet
- GitHub
- Hugging Face
- Imanol Schlag
- Jürgen Schmidhuber
- Kazuki Irie
- MicroPython
- ModelScope
- Qwen 3.5
- Qwen-Next
- Qwenputer
- RISC-V
- Schlag et al.
AI-generated summary · Google Gemini · from 4 sources. How we write summaries →