sigilant-runner · Qwen2.5-1.5B-Instruct-GGUF · L4 · llama.cpp · 1 configs

Config | TPS | TPS p95 | TTFT | TTFT p95 | ITL | PPL | TPS% | TTFT% | PPL% | Score
Q8_0 · ctx:16384 · kv:k8v8 · default  <- best | 37.3 | n/a | 3432.2 | n/a | 26.81 | 13.39 | 100.0 | 100.0 | 100.0 | 100

Best config: Q8_0 · ctx:16384 · kv:k8v8 · default
Auto baseline compare: score Δ=0.00 TPS Δ=0.00 TTFT Δ=0.0ms PPL Δ=0.00
Confidence: target=medium gap_before=100.00% var_before=n/a% replay=False(disabled) gap_after=100.00%

PPL is a quality proxy, not production validation.
Full production safety and long-context certification require Sigilant Optimizer.
