Background: The relationship between alpha 2-macroglobulin (A2M) gene and Alzheimer’s disease (AD) has been widely studied across populations; however, the results are inconsistent. Objective: This study aimed to evaluate the association of A2M gene with AD by the application of meta-analysis. Methods: Relevant studies were identified by comprehensive searches. The quality of each study was assessed using the Newcastle-Ottawa Scale. Allele and genotype frequencies were extracted from each of the included studies. Odds ratio (OR) with corresponding 95% confidence intervals (CI) was calculated using a random-effects or fixed-effects model. The Cochran Q statistic and I2 metric was used to evaluate heterogeneity, and Egger’s test and Funnel plot were used to assess publication bias. Results: A total of 62 studies were identified and included in the current meta-analysis. The G allele of rs226380 reduced AD risk (OR: 0.64, 95% CI: 0.47–0.87, pFDR = 0.012), but carrier with the TT genotype was more likely to develop AD in Asian populations (OR: 1.56, 95% CI: 1.12–2.19, pFDR = 0.0135). The V allele of the A2M-I/V (rs669) increased susceptibility to AD in female population (OR, 95% CI: 2.15, 1.38–3.35, pFDR = 0.0024); however, the II genotype could be a protective factor in these populations (OR, 95% CI: 0.43, 0.26–0.73, pFDR = 0.003). Sensitivity analyses confirmed the reliability of the original results. Conclusions: Existing evidence indicate that A2M single nucleotide polymorphisms (SNPs) may be associated with AD risk in sub-populations. Future studies with larger sample sizes will be necessary to confirm the results.