A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
- avx2
- c99
- cpu-inference
- deep-learning
89,572 visible repositories in the index
1–7 of 7 · Most stars
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
Locally run an Instruction-Tuned Chat-Style LLM
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案,结构参考alpaca
llama and other large language models on iOS and MacOS offline using GGML library.
Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)
Llama 2 Everywhere (L2E)
Source code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Python, Node.js and a shell built into the app.