*所有模型均使用 vLLM 进行评估，并采用各基准测试推荐的生成参数。这些结果使 LFM2.5-24B-A2B 成为需要推理、调用工具并在本地设备上可靠运行的智能体的强大基础。

*All the models were evaluated with vLLM, using each benchmark's recommended generation parameters. These results make LFM2.5-24B-A2B a strong foundation for agents that need to reason, call tools, and run reliably on your device.

*所有模型均使用 vLLM 进行评估，并采用各基准测试推荐的生成参数。这些结果使 LFM2.5-24B-A2B 成为需要推理、调用工具并在本地设备上可靠运行的智能体（agents）的坚实基座。GPU 推理方面，LFM2.5-24B-A2B 是其尺寸级别中最快的模型，在单张 B300 GPU 上高并发场景下可实现超过 21K 输出 tokens/秒的速度。当您需要具备推理能力、能调用工具且在本地设备上稳定运行的智能体时，请选择 LFM2.5-24B-A2B。

*All the models were evaluated with vLLM, using each benchmark's recommended generation parameters. These results make LFM2.5-24B-A2B a strong foundation for agents that need to reason, call tools, and run reliably on your device. GPU inference. LFM2.5-24B-A2B is the fastest model in its size class, reaching over 21K output tokens per second at high concurrency on a single B300. Reach for LFM2.5-24B-A2B when you need agents that reason, call tools, and run reliably on your device.