Qwenputer divagr.com ↗
A project that compiles CHIP-8 and RISC-V CPUs into Qwen model weights using Gated DeltaNet state as memory.
LibraryAI & MLllmcompileremulation
Recommended in 1 thread
Show HN: A working Nintendo in ~1GB of Qwen weightsgithub.com ·
It is the foundation this project builds on and commenters found it very cool.
Similar tools
- ExLlamaV3 AI & ML0 threads
A quantization and inference library for running LLMs on consumer and datacenter GPUs.
- 1 thread
- Heretic ↗AI & ML1 thread
An open-source tool for automatically removing refusal behavior from language models.
- 1 thread
- 1 thread
- Jeffy ↗AI & ML1 thread
An open-source library bundling pretrained task-specific classifiers that train and run locally on CPU.
- 1 thread
- 1 thread
Also in AI & ML
- 11 threads
- 7 threads
- DeepSeek6 threads
A family of large language models offered via a low-cost API.
- 6 threads
- 3 threads
- Claude3 threads
Anthropic's AI model and command-line assistant.
- 3 threads
- 3 threads
- 3 threads
- 3 threads
- Qwen3 threads
Alibaba's family of open-weight large language models.
- oh-my-pi3 threads
A setup built around the pi coding agent.
Link from a commenter, not checked or endorsed by us: ↗ https://divagr.com/blog/qwenputer