community pool / model answer

Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP

chat · HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP

58.4 tok/s · model median · 2 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Arc Pro B70 32GB4-bit58.4 tok/sreported2,13523.2 GB262,144llama.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.