NVIDIA RTX 3090 llama.cpp: Gemma4 31B (Q4_K) token generation at 16k context

THIRD-PARTY MEASURED (Hardware Corner GPU LLM Benchmarks page, tables dated March 2026). llama.cpp llama-bench, GGUF, single GPU, batch-1. NVIDIA RTX 3090. Gemma4 31B (Q4_K). Number is the 16k-context column of the Token Generation table: context depth the run was measured at, not a fixed pp512/tg128. Per-request, NOT aggregate. The 4k and deepest-context cells of this model were already filed; this is a missing intermediate context column.

Same page and protocol as the already-filed hc26-3090-gemma4-31b-q4k cells. Raw llama-bench logs are not published.