NVIDIA RTX A6000 llama.cpp: Llama 3.3 70B (Q4_K) token generation at 16k context
9.1 tok/s (tg16k, per-request batch-1)
Fields
id
benchmarks/hc26-a6000-llama33-70b-q4k-16k-tgMetric
decode_tok_s
Value
9.1
Unit
tok/s (tg16k, per-request batch-1)
Model
Llama 3.3 70B (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 A6000. Llama 3.3 70B (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.
Measured by
third_party
Reproducible
yes