Model Detail

Hy-MT2-30B-A3B is a large language model with 30B parameters released by tencent. The model is registered under the translation pipeline tag on Hugging Face, and supports text->text inputs, distributed under the permissive apache-2.0 license.

Hy-MT2-30B-A3B is priced at $0.074/M input tokens and $0.295/M output tokens. Operationally the model offers a 8K-token context window, which matters when sizing it for prompt-heavy or latency-sensitive workloads. At this input rate the model sits in the commodity tier and is suitable for high-volume workloads where per-call cost dominates the decision.

Hy-MT2-30B-A3B ships with 30B parameters. Total weight footprint is approximately 30.1 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.

Hy-MT2-30B-A3B is best fit for general-purpose chat and instruction-following workloads, translation and cross-lingual generation, and high-volume batch jobs where per-call cost dominates the budget. 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.