Liquid 这个 8B MoE 模型只用 4.8GB 内存就比 OpenAI 20B 模型多调用了一倍工具，速度还快两倍，本地跑 agent 任务很实用。
Liquid 的 LFM2.5-8B-A1B（8B总参、1B激活）在 MacBook Pro M5 Max 上本地运行，与 OpenAI 的 gpt-oss-20b 对比工具调用能力。面对需执行7个工具调用的旅行规划任务，LFM2.5-8B-A1B 全部成功，而 gpt-oss-20b 仅完成 3 个。内存方面，LFM2.5-8B-A1B 仅用 4.8 GB，远低于对手的 11 GB。速度上，LFM2.5-8B-A1B 达到 266 tok/s，总耗时 6.9 s，而 gpt-oss-20b 为 146 tok/s 和 15.0 s。该模型利用 38T 训练 token 的 MoE 架构，实现了小参数下的高效工具调用。
Liquid's LFM2.5-8B-A1B smashed OpenAI's gpt-oss-20…
Liquid's LFM2.5-8B-A1B smashed OpenAI's gpt-oss-20b on tool calling
We ran both locally on a MacBook Pro M5 Max, 64GB, and gave each the same trip-planning request that only completes if the model fires all 7 tool calls - weather for 3 cities, two currency conversions, an email and a reminder
Outputs: LFM2.5-8B-A1B: 4.8 GB RAM usage, 7/7 tool-calls, 266 tok/s, 6.9s OpenAI gpt-oss-20b: 11 GB RAM usage, 3/7 tool-calls, 146 tok/s, 15.0s
The 8B used less than half the RAM and still fired all 7 calls, while the 20B silently dropped more than half of its own. It also ran ~2x faster, wrapping the full agentic request in 6.9s against 15s. That's what 38T training tokens buy: a 1B-active MoE that nails the agentic tool calls a model 2.5x its active size keeps dropping