Fastest
fairy:latest
4.0B
90.8 tok/s
Highest token generation speed at 90.8 tok/s.
Hardware Benchmarks
Compare Apple M5 Pro benchmark results and see which models actually earn the best completed quality scores.
GPU-specific specifications for local LLM planning.
Models we recommend for Apple M5 Pro.
Fastest
4.0B
Highest token generation speed at 90.8 tok/s.
Best quality & Largest context
27.8B
Highest completed quality score at 81.0. Largest context that fits in 64GB VRAM, at 32,768 tokens.
Completed quality-ranked benchmark results for Apple M5 Pro.