Inty News
@__Inty__
欢迎进我的聊天群 👉
加入 August 2018
53 正在关注 750K 粉丝
1 token/秒
😂
You can Run DeepSeek V4 Flash (33B MoE) running on 8 GB RAM, CPU-only, zero GPU.
- Cold first-token: 5.33s
- Max RSS: 5.9-6.2 GiB
- Process swaps: 0
The entire model stayed memory-mapped on NVMe. Linux demand-paged only the needed weights into RAM.
This is not fast, It’s not production.
But it proves something important: Model size vs RAM is now a performance problem, not a hard barrier.
VRAM, RAM, NVMe is becoming a real memory hierarchy for local AI.
-
显示更多
