Lao Guo's Learning Space
Nov 20, 2026 · Artificial Intelligence
Splash vs llama.cpp: 5× Speed Claim Tested – Benchmarks, Caveats & Mac Hardware Requirements
The article analyzes Splash, a Mac-specific LLM inference engine claiming 5× speed over llama.cpp, but reveals caveats: the project is not new, "278 models" is a mistranslation of 27B, 210 tok/s only under narrow conditions, model support is limited to a few Qwen variants, and it requires at least 36GB unified memory on M3+ Macs.
Apple SiliconDFlashLLM inference
0 likes · 12 min read
