community pool / model answer

Qwopus3.6-35B-A3B-v1-MTP-GGUF

chat · Jackrong/Qwopus3.6-35B-A3B-v1-MTP-GGUF

92.8 tok/s · model median · 6 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit91.6 tok/smeasured2,37421 GB32,768llama.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.