Gemma 4 可以通过洗车测试

预感今年的本地小模型要全面崛起了。

mlx 量化的好像也出来

有没有可能这些测试题都被硬编码进去了，就像之前 9.11 比大小和草莓几个 r 这种问题，之前会被硬编码进模型。

这个问题被传播太广了，估计已经进题库了。

一个单一片面的问题不能说明什么吧，不用死磕一个问题，个人观点。

嗯嗯

@tool2dx 没那么容易,即使内存供应没问题,30B 以上,能产生 20 token/s 的本地机器也是大家伙,无法便携.

qwen3.5-27b 也可以，如果可以再缩小 10 倍，估计未来很多都可以本地运行低级任务 + 远程的高级任务

@gkiwi Qwen3.5 你遇到过那种他思考了几分钟然后直接超时的情况吗

能解开道德限制吗？之前 gemma3 道德限制比 Gemini 都邪门

这是题库了

刚试了 qwen3.6-plus ，回答还是错的。

At just 50 meters (about 164 feet), you should definitely walk. Here’s why:

⏱️ Faster overall: Starting the car, backing out, driving 50m, finding a spot, and parking will almost certainly take longer than a 30–40 second walk. ⛽ Saves fuel & reduces wear: Short trips like this are highly inefficient for combustion engines. They don’t reach optimal operating temperature, which increases fuel consumption, oil dilution, and long-term wear. (Even in an EV, it’s unnecessary energy use.) 🌍 Zero emissions: Walking for 50 meters has no carbon footprint. 💡 Practical tip: Unless you’re carrying heavy equipment, have mobility limitations, or it’s actively pouring rain, walking is the smarter choice.

Grab your supplies, enjoy the short stroll, and save your car the pointless start-stop cycle. Your wallet, engine, and the environment will thank you. 🚶‍♂️🚗💨

@Livid 应该是推理产生很多 token ，max_tokens 设置太大了

deepseek 之前不行，现在也可以了，感觉针对性训练过