Qwen3.8 27Bqwen38_27b_c1_personal
3,250 tok/s
113.3 tok/s
Source-backed
ModelDock / hardware record
Compare the published model-specific reading / prefill and single-stream writing / decode results for 2× RTX 5070 Ti.
Available model records
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.