GitHub · Python
logxio/picchio
Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.
- Stars
- 17
- Forks
- 2
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: apple-silicon, benchmark, cuda, diagnostics, gguf, gpu, gpu-benchmark, gpu-monitoring, linux, llama-cpp
Latest data point: Nov 21, 2026 · 17 stars · 2 forks