community pool / model answer

gemma-4-26B-A4B-it-ultra-uncensored-heretic-GGUF

chat · llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic-GGUF

88.2 tok/s · model median · 1 runs in the model record.

Answer

88.2tok/s

reportedVII 16GB4-bit · 1 run · decodebest cell in the pool

  1. VII 16GB88.2 tok/sreported1 run · peak VRAM no data yet · 16 GB rig memory
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
VII 16GB4-bit88.2 tok/sreported463- 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.