community pool / model answer

Unlimited-OCR

chat · baidu/Unlimited-OCR

365.5 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB16-bit365.5 tok/sreported2322.3 GB2,048sglang

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.