Back to home
Apple Silicon
2 articles tagged with this topic
llama.cppQwen
37 LLMs Benchmarked on MacBook Air M5 32GB: Full Speed Results
Community benchmark of 37 local LLMs on M5 Air 32GB using llama-bench reveals MoE models as clear winners for speed-to-quality ratio.
Apr 62 min read
Gemmallama.cpp
Real-Time Multimodal AI Runs Locally on M3 Pro with Gemma E2B
Developer runs Gemma 4 E2B locally on Apple M3 Pro for real-time audio/video input with voice output using the Parlor repo.
Apr 51 min read