ModelDock / hardware record

Mac Studio M5 Max 64 GB local AI benchmarks

Compare the published model-specific reading / prefill and single-stream writing / decode results for Mac Studio M5 Max 64 GB.

Memory64 GBPublished model records: 2

Available model records

Mac Studio M5 Max 64 GB performance by model

ModelReading / prefillWriting / decodeEvidenceAs of

Qwen3.8 27Bqwen38_27b_c1_personal

~745 tok/s

~59.2 tok/s

Scaled estimate

2026-08-15

View DataNo fabricated Evidence record

Qwen3.8 Flash Nextqwen38_flash_next_c1_personal

~517.9 tok/s

~36 tok/s

Scaled estimate

2026-08-28

View DataNo fabricated Evidence record

Reading / prefill

Prefill · tok/s

Writing / decode

Decode · single stream · tok/s

Evidence

Each row is one hardware × model record. Source observations stay on Evidence; projections link to their calibration details on Data.