The current evidence regarding the association between vitamin D deficiency and cardiovascular diseases/metabolic disorders is contradictory and inconclusive. In this large-scale observational study, we investigated the relationship between the serum 25-hydroxy vitamin D3 [25(OH)D] concentration and subclinical atherosclerosis in an elderly Asian population. In the I-Lan longitudinal study (ILAS), 1798 elderly, aged 50 and older, were enrolled. For each subject, serum 25-hydroxy vitamin D3 [25(OH)D] concentration and demographic data were recorded. The participants were divided into two groups according to their serum 25(OH)D level (sufficient, > 20 ng/mL and deficient, ≤ 20 ng/mL). Carotid intima-media thickness (cIMT) was measured at bilateral common carotid arteries. Subclinical atherosclerosis was defined as a mean cIMT > 0.81 mm. The mean subject age was 64 ± 9 years old, and 604 (33.6%) were identified as having serum 25(OH)D level ≤ 20 ng/mL. Subjects with serum 25(OH)D level ≤ 20 ng/mL were younger, more likely to be female and smoker, and had a higher incidence of hypertension, dyslipidemia, and metabolic syndrome, compared to those with serum 25(OH)D level > 20 ng/mL. Additionally, patients with serum 25(OH)D level ≤ 20 ng/mL were associated with a lower risk of subclinical atherosclerosis (crude OR: 0.63, 95% CI 0.50–0.81, p < 0.001), according to univariate analysis. However, after adjusting for gender and age, serum 25(OH)D level ≤ 20 ng/mL was not a significant risk factor for subclinical atherosclerosis. Serum 25(OH)D level ≤ 20 ng/mL was not an independent risk factor for subclinical atherosclerosis in this large elderly Asian population. Association observed in the univariate analysis may be confounded by gender or comorbidities.