Hardware Corner: RTX 5060 Ti 16GB, llama.cpp CUDA, Qwen3 8B Q4_K_XL GGUF, decode 51.41 t/s @16k ctx
51.41 tok/s per-request decode (batch 1, ~16384-token context)
Fields
id
benchmarks/hwcorner-rtx-5060-ti-qwen3-8b-q4kxl-decode-16kMetric
decode_tok_s
Value
51.41
Unit
tok/s per-request decode (batch 1, ~16384-token context)
Model
Qwen3 8B Q4_K XL GGUF
Methodology
THIRD-PARTY MEASURED (hardware-corner.net Definitive GPU Ranking for LLMs, accessed 2026-10-15). llama.cpp llama-bench CUDA 12.8, Ubuntu 24.04, Q4_K_XL GGUF quants, decode tok/s per GPU per model at ~16K context. Per-request batch-1, NOT aggregate. Value is the 16K-context column.
Measured by
third_party
Reproducible
yes
notes
HC names this card 'best price-to-performance' pick in the 16GB tier.
Notes
HC names this card 'best price-to-performance' pick in the 16GB tier.