sipsalabs / ultracompress Star 12 Code Issues Pull requests Discussions Near-lossless 5-bit transformer compression - 23 architectures verified across 4 classes (dense + MoE + SSM + ViT, 0.6B-405B). Hermes-3-405B 1.0066x, Phi-4 1.00506x. SHA-256-verifiable, reproducible reconstruction. OpenAI-compatible API at api.sipsalabs.com. pip install ultracompress python compression cuda inference pytorch transformer lossless quantization mlops deep-tech openai-api llm patent-pending ai-infrastructure 405b consumer-gpu 5-bit sipsa-labs experimental-tech Updated May 29, 2026 Python