RTX 5070 Ti llama.cpp: Qwen3 8B prefill at 16k (Hardware Corner per-card page)

Hardware Corner per-card LLM benchmark page (March 2026 sweep). Same lab method as their RTX 5090 llama-bench series already ingested: llama.cpp llama-bench, Ubuntu 24.04, CUDA 12.8, Q4_K GGUF (gpt-oss 20B labeled MXFP4 on the page; filed under gguf-mxfp4-moe, the nearest schema format). Context depth 16k. Per-request, batch size 1, NOT aggregate across concurrent requests. The page does not print the llama.cpp commit or the exact prompt/output lengths; the sibling 5090 series used build 466c1911 with -fa 1 -ngl 99. That protocol is the likely one and is NOT asserted as measured on this card. Prompt processing 3653.8 tok/s.

Transcribed from the Hardware Corner RTX 5070 Ti per-card page (header: Updated Benchmarks March 2026), not from the Dec 2025 ranking table. The two pages disagree on the same cell: Qwen3 8B decode at 16k is 87.5 here and 127.72 on the ranking, so this record is status: contested. 16 GB GDDR7, 896 GB/s, 300 W. Page states gpt-oss 20B MXFP4 runs at a full 128k context in VRAM and that 30B+ models do not fit.