Extropic Z1T
by Extropic · Model · Language & code models
Z1T-0 sparse transformer weights released on Hugging Face with full training recipe; no inference provider, no text inference script
AccessOpen weightsLicenseApache 2.0 (code repository; the weights' license is not stated)
Evidence
- Sep 5JAX training code on GitHub can train the sparse models on a normal GPU as simulation; it does not run the released weights
- Sep 5Needs about 10x more compute than GPT-2 for equal quality, but each operation uses far less energy, so total energy is claimed lower