mehulmpt· @mehulmpt · X·· 25 天前AI 评分
开发者实测 MiniCPM5-2B：2B 参数本地跑出同尺寸最强表现
开发者 mehulmpt 表示近期一直在业余测试 gemma e4b、qwen 4b 等超小参数 LLM，拿到 2B dense 参数的 MiniCPM5-2B 后认为它在同尺寸中表现出色。该模型支持 128k context window，通过 llama.cpp 在他的 macbook pro m5 上完全本地运行，表现优于同尺寸范围内的所有模型。
open source is on fire this week! for some weeks, i've been playing with very small LLM models in my free time (gemma e4b, qwen 4b, etc.) just to see what “small” stuff these LLMs can do.
I got access to this 2 billion dense param model MiniCPM5-2B, and this thing is a beast for its size. 128k context window and better than every model in the same size range running fully locally on my macbook pro m5 (via llama.cpp)
来源：mehulmpt · x.com