Model Detail

Laguna-S-2.1-INT4 is a code generation model with 60.6B parameters released by poolside. The model is registered under the text-generation pipeline tag on Hugging Face, released under the openmdw-1.1 license.

Laguna-S-2.1-INT4 ships with 60.6B parameters, distributed as a quantized weight variant for lower-VRAM inference. Total weight footprint is approximately 121.1 GB, which is the relevant figure when planning local-inference VRAM. Distribution is governed by the openmdw-1.1 license — review the exact terms before commercial deployment.

Laguna-S-2.1-INT4 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.