jevIMAGE
用 llama.cpp 补丁在本地 CPU 跑 Jev 决策模型
演示 421M 参数的 Laya 模型纯 CPU 运行、峰值仅占 1GB 内存，决策准确率接近 Jev 且无 API 费用。
Hikari∣LocalLLM⚡
@Hikari_07_jp29 天前收录原推发布于 2026.10.03
Hikari∣LocalLLM⚡ @Hikari_07_jp原推发布于 2026.10.03
You can run Jev locally using the https://atomic.chat llama.cpp patch! This demo is running on the CPU. Laya has 421M parameters and requires only 1GB of memory at peak usage. ・Decision-making accuracy comparable to Jev ・Faster performance ・No API fees.
这条是引用着另一条写的：x.com/atomic_chat_hq/status/2106145162762109160
x.com/hikari_07_jp/status/2106320874718835091采集于 2026.10.04 10:05