community pool / model answer

GLM-Z1-Rumination-32B-0414

chat · zai-org/GLM-Z1-Rumination-32B-0414

19.7 tok/s · model median · 11 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit15.8 tok/smeasured-2.3 GB8,192llama.cpp
RTX 3090 24GB4-bit21.3 tok/smeasured-- GB65,536llama.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.