Model Detail

ice-012-audio is a code generation model with 357M parameters released by fanuonai. The model is registered under the text-to-speech pipeline tag on Hugging Face, distributed under the permissive cc-by-nc-4.0 license.

ice-012-audio ships with 357M parameters. The cc-by-nc-4.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.

ice-012-audio is best fit for code completion, repository-scale Q&A, and pair-programming integrations. 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.