Skip to content
@sipsalabs

sipsalabs

Sipsa Labs

A research lab — Systems · Intelligence · Precision. UltraCompress is our flagship publicly-shipped product.


What we ship publicly

Extreme compression infrastructure for large language models. The only sub-3-bits-per-weight method we evaluated on a 6-model head-to-head benchmark with zero catastrophic failures.

pip install ultracompress

Apache-2.0 CLI. Pre-compressed reference models distributed via the Hugging Face Hub (rolling release through April–May 2026).

Patent pending — USPTO 64/049,511 + 64/049,517, filed April 25, 2026.


What's coming

  • v0.1 alpha — pre-compressed reference models for Qwen3, Llama, Mistral families releasing throughout April–May 2026
  • v0.2 (Q3 2026)uc compress (self-compression of customer models) + Track B architectural-compression variants + native exports to llama.cpp, vLLM, TensorRT-LLM, CoreML

Contact

sipsalabs.com

Popular repositories Loading

  1. ultracompress ultracompress Public

    Extreme compression infrastructure for large language models. pip install ultracompress

    Python 1

  2. .github .github Public

    Sipsa Labs organization profile

Repositories

Showing 2 of 2 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…