# swiftpick-30B-A3B decision model by harishvs > swiftpick-30B-A3B is a text-only Nemotron decision adapter. Read its tagged runtime, hardware needs, reported tests and NVIDIA licence. Updated 2026-11-07 (Australia/Adelaide) ## Quick answers ### What is swiftpick-30B-A3B by harishvs? [swiftpick-30B-A3B](): A text-only decision adapter and readout head on Nemotron-3-Nano-Omni-30B-A3B. [swiftpick-30B-A3B facts]() [Source]() ### Who makes swiftpick-30B-A3B? [swiftpick-30B-A3B](): harishvs [swiftpick-30B-A3B facts]() [Source]() By harishvs · Hugging Face package release: 2026-11-05 · CUSTOM LICENCE A text-only decision adapter and readout head on Nemotron-3-Nano-Omni-30B-A3B. It uses the base’s text decoder, despite the multimodal base name. The adapter combines three training runs. Its loader is on the swiftpick-30B-A3B-v1 tag of strands-decider; main and released package versions cannot load this base. ## Facts - Base: Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 text decoder - Inputs: Text; choice, noul and score - Licence: NVIDIA Open Model Agreement for the model derivative; code Apache-2.0 - Hardware: 62.5 GB bf16 base download; one 80 GB GPU or multiple GPUs, plus CUDA Mamba kernels - Access: Public adapter and head; tagged strands-decider runtime ## Claims and sources - **VENDOR-REPORTED**: The maker reports 183 of 231 public [JevBench]() items correct (79.22%), Brier 0.287 and ECE 0.059 at a 4,096-token window. Its separate 42.4 Intelligence estimate uses only the open half of the v1.5 method and omits sealed items and other axes; it is not an official score or rank. Questions are sometimes under-read, and calibration transfers poorly beyond the fitted short tasks. [source]() ## Links - [Source: Model card and files]() ## Related projects No related projects are listed in the registry.