This paper introduces Bhasha-Rupantarika, a light and efficient multilingual translation system tailored through algorithm-hardware codesign for resource-limited settings. The method investigates model deployment at sub-octet precision levels (FP8, INT8, INT4, and FP4), with experimental results indicating a 4.1× reduction in model size (FP4) and a 4.2× speedup in inference speed, which correlates with an increased throughput of 66 tokens/s (improvement by 4.8×). This underscores the importance of ultra-low precision quantization for real-time deployment in IoT devices using FPGA accelerators, achieving performance on par with expectations. Our evaluation covers bidirectional translation between Indian and international languages, showcasing its adaptability in low-resource linguistic contexts. The FPGA deployment demonstrated a 1.96× reduction in LUTs, a 1.65× decrease in FFs, resulting in a 2.2× enhancement in throughput compared to OPU and 4.6× compared to HPTA. Overall, the evaluation provides a viable solution based on quantization-aware translation along with hardware efficiency suitable for deployable multilingual AI systems. The entire codes and dataset for reproducibility are publicly available, facilitating rapid integration and further development by researchers.