ModelDock / hardware record

RTX 4080 Super local AI benchmarks

Compare the published model-specific reading / prefill and single-stream writing / decode results for RTX 4080 Super.

Memory16 GBPublished model records: 1

Available model records

RTX 4080 Super performance by model

ModelReading / prefillWriting / decodeEvidenceAs of

Qwen3.8 27Bqwen38_27b_c1_personal

1,750 tok/s

43.6 tok/s

Source-backed

2026-08-18

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.