1
Ask HN: Are current on-device LLMs useless?
1.2B参数的端侧模型仅回应"hey"便说出"heat"，糟糕表现引发对移动端大模型实用性的质疑。
I found this model "lfm2.5-thinking" which is "designed for on-device deployment" and is really tiny: just 1.2b params (~700 MB) My first and very sho…