NVIDIA RTX 5090 llama.cpp: Gemma4 26B (Q4_K) prompt processing at 128k context
2839.1 tok/s (pp128k, per-request batch-1)
Fields
id
benchmarks/hc26-5090-gemma4-26b-q4k-128k-ppMetric
prefill_tok_s
Value
2,839.1
Unit
tok/s (pp128k, per-request batch-1)
Model
Gemma4 26B (Q4_K)
Methodology
THIRD-PARTY MEASURED (Hardware Corner GPU LLM Benchmarks page, tables dated March 2026). llama.cpp llama-bench, GGUF, single GPU, batch-1. NVIDIA RTX 5090. Gemma4 26B (Q4_K). Number is the 128k-context column of the Prompt Processing table: context depth the run was measured at, not a fixed pp512/tg128. Per-request, NOT aggregate.
Measured by
third_party
Reproducible
yes