ModelDock / hardware record

RTX 3090 Ti local AI benchmarks

Compare the published model-specific reading / prefill and single-stream writing / decode results for RTX 3090 Ti.

Memory24 GBPublished model records: 2

Model-independent specification

Durable hardware facts.

Configured capacity and peak physical bandwidth feed the Hardware ranking. Model throughput remains in the hardware × model records below.

Memory24 GBDedicated

Peak bandwidth1,008 GB/sSingle device

Form factorGPU card1 ×

Specification statusDerived specOpen public specification ↗

Available model records

ModelReading / prefillWriting / decodeEvidenceAs of

Qwen3.8 27Bqwen38_27b_c1_personal

1,458.3 tok/s

69.8 tok/s

Source-backed

2026-08-18

Qwen3.8 Flash Nextqwen38_flash_next_c1_personal

~2,255.1 tok/s

~93.1 tok/s

Scaled estimate

2026-10-05

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.