Fastest
mtplx-qwen38-27b-oq4e-fp16-mtp
27B
486.9 tok/s
Highest token generation speed at 486.9 tok/s.
Hardware Benchmarks
Best Local LLM Performance for Apple M5 Pro
Compare Apple M5 Pro benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 64GB
Recommended Models
Models we recommend for Apple M5 Pro.
Best quality & Largest context
ukisai/Swift-1.5-Qwen3.8-27B-GGUF:Q6_K
27B
34.9 tok/sQuality 91.1Context 65,536 tokens
Highest completed quality score at 91.1. Largest context that fits in 64GB VRAM, at 65,536 tokens.
Models on the Apple M5 Pro
Every model the community ran on this hardware. Up is better answers, right is faster. Time to finish counts every token the model wrote, thinking included, so a model that talks a lot ends up further left.
Best trade-off: quality 60+, and nothing else here is both faster and betterOther models · dot size = number of runs
Medians over 23 fully rated runs of 18 models. Each quantization is its own model.
Frequently asked questions
Which models actually run best on the Apple M5 Pro, by task, from community benchmark data.
- What is the best local model for coding on the Apple M5 Pro?
- On the Apple M5 Pro, ukisai/Swift-1.5-Qwen3.8-27B-GGUF:Q6_K ranks first for coding in our benchmarks (92.9/100 at ~34.9 tok/s).
- What is the best local model for agentic workflows on the Apple M5 Pro?
- On the Apple M5 Pro, unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M ranks first for agentic workflows in our benchmarks (92.1/100 at ~28.3 tok/s). ukisai/Swift-1.5-Qwen3.8-27B-GGUF:Q6_K is faster (~34.9 tok/s) and still scores well (90.1/100) — a good pick if you'd rather trade a little quality for speed.
Benchmark Results
Completed quality-ranked benchmark results for Apple M5 Pro.