community pool / model answer

supergemma4-26b-uncensored-gguf-v2

chat · Jiunsong/supergemma4-26b-uncensored-gguf-v2

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5060 Ti 16GB ×24-bit89.4 tok/sreported125- GB32,768llama.cpp
Ryzen AI Max 395 128GB4-bit66.1 tok/sreported-22.3 GB16,384llama.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.