community pool / model answer

Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF-Q8-NVFP4

chat · AIconjured/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF-Q8-NVFP4

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

Answer

73.8tok/s

reportedRTX PRO 6000 Blackwell 96GB4-bit · 2 runs · decodebest cell in the pool

  1. RTX PRO 6000 Blackwell 96GB73.8 tok/sreported2 runs · peak VRAM no data yet · 96 GB rig memory
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX PRO 6000 Blackwell 96GB4-bit73.8 tok/sreported91- 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.