Hardware Corner Dec 2025 ranking: RTX Pro 6000, llama.cpp CUDA, gpt-oss 120B Q4_K_XL GGUF (MXFP4), prefill 4060.65 t/s @16K ctx

THIRD-PARTY LAB MEASURED (hardware-corner.net The Definitive GPU Ranking for LLMs, Allan Witt, updated December 9, 2025; the page states every number was captured on-hardware in their lab). llama.cpp llama-bench, Ubuntu 24.04, CUDA 12.8, 4-bit Q4_K_XL GGUF for every model (gpt-oss ships MXFP4). Prompt Processing table, 16K context column. ONE request, batch size 1: the table prints prefill tok/s of a single stream filling that KV depth, NOT aggregate across concurrent requests. The page does not publish the llama.cpp build hash or the exact prompt and output token counts beyond the context-depth bucket, and it does not say how many repetitions were averaged.

format_id is the nearest standard GGUF in this repo; the page labels the quant Q4_K_XL (gpt-oss is MXFP4). A dash in the source table means the context did not fit and is not recorded. The RTX 4090 48GB modded row on the same page has no accelerator record and is excluded. Cells whose numeric value already existed in another record are skipped so the same measurement is not stored twice. This is the prompt-processing half of the ranking; the token-generation half was filed as hc-rank records.