community pool / model answer

Ornstein3.6-27B-MTP-NSC-ACE-SABER-GGUF

chat · GestaltLabs/Ornstein3.6-27B-MTP-NSC-ACE-SABER-GGUF

30.2 tok/s · model median · 17 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB4-bit20.9 tok/smeasured-22.6 GB262,144llama.cpp
RTX 3090 24GB ×24-bit49.5 tok/sreported129- GB2,048llama.cpp
RTX 3090 24GB ×26-bit47.2 tok/smeasured202- GB2,048llama.cpp

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.