ModelDock
Qwen3.8 27Bqwen38_27b_c1_personal
~1,075 tok/s
~91 tok/s
Scaled estimate
View DataNo fabricated Evidence record
ModelDock / hardware record
Mac Studio M5 Ultra 256 GB local AI benchmarks
Compare the published model-specific reading / prefill and single-stream writing / decode results for Mac Studio M5 Ultra 256 GB.
Memory256 GBPublished model records: 2
Available model records
Mac Studio M5 Ultra 256 GB performance by model
ModelReading / prefillWriting / decodeEvidenceAs of
Qwen3.8 Flash Nextqwen38_flash_next_c1_personal
~1,012.2 tok/s
~70.4 tok/s
Scaled estimate
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.