Hardware Corner Mar-2026: nvidia-rtx-4070-ti llama.cpp Qwen3 8B Q4_K GGUF token generation 57.6 tok/s at 16k context

THIRD-PARTY MEASURED (hardware-corner.net /gpu-llm-benchmarks/rtx-4070-ti/, page updated March 2026, accessed 2026-10-16). llama.cpp llama-bench, GGUF, single GPU, full offload. The page publishes prompt-processing tok/s and token-generation tok/s by context tier; it does not state the llama.cpp build, the prompt length, the generation length, or whether flash attention was enabled. Value is the 16k context column. Per-request batch-1, NOT aggregate across concurrent requests.

Context tier is the page bucket, not an exact measured token count. Page quant Q4_K maps to gguf-q4-k-m; page MXFP4 maps to gguf-mxfp4-moe. Distinct from the older Q4_K_XL 16k-decode rows sourced from hardware-corner-gpu-ranking-local-llm.