Model Detail

WeVisDoc-4B is an AI model with 4B parameters released by tencent. Distributed under the permissive apache-2.0 license.

WeVisDoc-4B ships with 4B parameters. Total weight footprint is approximately 4.4 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.

WeVisDoc-4B is best fit for general-purpose AI workloads. 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.