Multiverse Computing announced the release of Pulsar 16B, a 16.15B-parameter open reasoning model built on NVIDIA Nemotron architecture, on June 23, 2026, in Donostia, Spain. Developed using Multiverse Computing’s proprietary technology and validated on NVIDIA accelerated computing infrastructure, Pulsar 16B delivers the reasoning performance of leading 30B-class architectures at roughly half the parameter count. Available in BF16, FP8, and NVFP4 precisions on HuggingFace under the Apache 2.0 license, the model matches its 30B-class starting point across standard benchmarks and outperforms gpt-oss-20B on nearly every measure. Key benchmark scores include AIME 2025 at 87.22, GPQA-Diamond at 71.41, and outperformance of gpt-oss-20B by 14 points on instruction following (IFBench), 11 points on function calling (BFCL-v4), and 15 points on math reasoning (AIME). With 32 concurrent requests on an NVIDIA Blackwell GPU, Pulsar 16B (FP8) delivers 4,808 tokens/second system throughput, a 43% increase over the base model's 3,363 tok/s, while reducing time-to-first-token from 2.18s to 1.24s. Long-context needle-in-a-haystack retrieval remains essentially perfect on both sides of the