NVIDIA RTX 5080 llama.cpp: gpt-oss 20B (MXFP4) prompt processing at 128k context
1726.6 tok/s (pp128k, per-request batch-1)
Fields
id
benchmarks/hc26-5080-gptoss-20b-mxfp4-128k-ppMetric
prefill_tok_s
Value
1,726.6
Unit
tok/s (pp128k, per-request batch-1)
Model
gpt-oss 20B (MXFP4)
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 5080. gpt-oss 20B (MXFP4). 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. Page annotates llama.cpp build 8233 on this model.
Measured by
third_party
Reproducible
yes