community pool / model answer

Ling-2.6-flash

chat · inclusionAI/Ling-2.6-flash

86.2 tok/s · model median · 8 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX PRO 6000 Blackwell Workstation Edition 96GB4-bit86.2 tok/smeasured7,71483.1 GB65,536sglang

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.