NVIDIA RTX 5080 llama.cpp: Qwen3 8B (Q4_K) token generation at 64k context
49.0 tok/s (tg64k, per-request batch-1)
Fields
id
benchmarks/hc26-5080-qwen3-8b-q4k-64k-tgMetric
decode_tok_s
Value
49
Unit
tok/s (tg64k, per-request batch-1)
Model
Qwen3 8B (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 5080. Qwen3 8B (Q4_K). Number is the 64k-context column of the Token Generation table: context depth the run was measured at, not a fixed pp512/tg128. Per-request, NOT aggregate.
Measured by
third_party
Reproducible
yes