Model Detail

zembed-1-embedding is a code generation model with 4B parameters released by zeroentropy. The model is registered under the feature-extraction pipeline tag on Hugging Face, distributed under the permissive cc-by-nc-4.0 license.

zembed-1-embedding ships with 4B parameters. Total weight footprint is approximately 4.0 GB, which is the relevant figure when planning local-inference VRAM. The cc-by-nc-4.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.

zembed-1-embedding is best fit for code completion, repository-scale Q&A, and pair-programming integrations, and semantic search, retrieval, and clustering pipelines. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.