{"as_of":"2026-10-12","license":"CC-BY-4.0","license_url":"https://creativecommons.org/licenses/by/4.0/","cite_as":"The Local Bench (thelocalbench.com), data as of 2026-10-12, CC BY 4.0","source_url":"https://thelocalbench.com","hardware":{"id":"rtx-4060-ti-16g","name":"GeForce RTX 4060 Ti 16 GB","vendor":"NVIDIA","class":"Discrete GPU","kind":"gpu","as_of":"2026-10-12","summary":"Cheapest new 16 GB card. Narrow 128-bit bus caps decode speed.","memory_gb":{"value":16,"flag":"sourced","unit":"GB","source":"https://www.nvidia.com/en-us/geforce/graphics-cards/40-series/rtx-4060-4060ti/","note":"16 GB variant, nvidia.com, checked 2026-10-12."},"bandwidth_gbs":{"value":288,"flag":"sourced","unit":"GB/s","source":"https://en.wikipedia.org/wiki/GeForce_RTX_40_series","note":"NVIDIA's GeForce spec pages list bus width but not bandwidth; figure from the cited Wikipedia spec table (bus width cross-checked on nvidia.com, 2026-10-12)."},"fp16_tflops":{"value":44,"flag":"sample","unit":"TFLOPS","note":"Sample FP16 dense compute; pending vendor-sheet citation."},"host_ram_gb":{"value":32,"flag":"sample","unit":"GB","note":"Assumed host RAM for offload."},"host_bandwidth_gbs":{"value":64,"flag":"sample","unit":"GB/s"},"load_watts":{"value":230,"flag":"sample","unit":"W","note":"Sample wall power under load."},"tdp_w":{"value":165,"flag":"sourced","unit":"W","source":"https://www.nvidia.com/en-us/geforce/graphics-cards/40-series/rtx-4060-4060ti/","note":"Total Graphics Power (16 GB variant), nvidia.com."},"price_usd":{"value":844.37,"flag":"estimate","unit":"USD","source":"https://www.newegg.ca/p/pl?d=rtx+4060+ti+16gb&N=4131","note":"No valid new 16 GB listing found on Newegg US; Newegg Canada price ÷ 1.4271 (Bank of Canada)."},"price_cad":{"value":1205,"flag":"sourced","unit":"CAD","source":"https://www.newegg.ca/p/pl?d=rtx+4060+ti+16gb&N=4131","note":"Lowest new in-stock 16 GB listing on Newegg Canada (MSI Gaming). Checked 2026-10-12."}},"runs":[{"model":"llama-2-7b","hardware":"rtx-4060-ti-16g","quant":"Q4_0","runtime":"llama.cpp (CUDA)","test":"tg128","tok_s":63.86,"flag":"sourced","date":"2026-10-12","source":"https://github.com/ggml-org/llama.cpp/discussions/15013","note":"Llama 2 7B Q4_0, llama-bench tg128, full GPU offload, flash attention off, single GPU. Community scoreboard entry; commit and submitter in the source table. Measured on the 8 GB variant (same 288 GB/s bus); treat as indicative for the 16 GB card.","min":63.85,"max":63.87}]}