best tencent open source llm 2026

The quantisation benchmarks show minimal performance degradation. On the DROP benchmark, the Hunyuan-7B-Instruct model scores 85.9 in its base B16 format, 86.0 with FP8, and 85.7 with Int4 GPTQ, indicating that efficiency gains do not come at a cost to accuracy.For deployment, Tencent recommends using established frameworks like TensorRT-LLM, vLLM, or SGLang to serve the Hunyuan models and create OpenAI-compatible API endpoints, ensuring they can be integr

Tenfold Capacity Expansion After Surge in Tencent Hy4 Invocations; No. 1 Among Open-Source Models in Agent Capabilities 2026-11-06 10:00:11 Source: QbitAI On November 5, Tencent announced that WorkBuddy had expanded tenfold in response to a surge in Hy4 invocations On November 5, Tencent announced that WorkBuddy had expanded tenfold in response to a surge in Hy4 invocations, in order to meet the experience and usage needs of more users. Meanwhile, driven b