NVIDIA RTX 3060 12GB llama.cpp: Qwen3 8B (Q4_K) token generation at 32k context
31.9 tok/s (tg32k, per-request batch-1)
Fields
id
benchmarks/hc26-3060-qwen3-8b-q4k-32k-tgMetric
decode_tok_s
Value
31.9
Unit
tok/s (tg32k, 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 3060 12GB. Qwen3 8B (Q4_K). Number is the 32k-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