 |
自己攒了个 comfyui 交流社区 nicolaszhao4 • 3h 45m ago • Lastly replied by songche | 9 |
 |
RTX PRO 5000（或其他 48GB 显存）的 Qwen3.8-27B-FP8 配置交流（prefill 5000+t/s， decode 60+t/s） sentinelK • 6h 24m ago • Lastly replied by gardenqaq | 54 |
 |
老哥们，预算 3w 左右想弄一套小型化本地大模型硬件，求推荐 turing518 • 1 day ago • Lastly replied by coefu | 14 |
 |
mac ultra deepseek harness & qwen3.8-27B 几点经验 coefu • 9h 42m ago • Lastly replied by coefu | 8 |
 |
个人是否应该投资购买 DGX Spark 之类的硬件来跑开源模型？既是自用，也是某种防止硬件涨价的投资？ sillydaddy • 5h 24m ago • Lastly replied by cherylaskinnero6 | 64 |
 |
qwen3.8 本机部署后搭配什么搜索工具呢？ idblife • 2 days ago • Lastly replied by coefu | 8 |
 |
local.ai 接力是干嘛呀？ justmiho • 2 days ago • Lastly replied by yuusha2022 | 24 |
 |
想本地化最小成本部署 qwen3.8 27b 求个配置建议 BingoW • 2 days ago • Lastly replied by coefu | 13 |
 |
local.ai 接力， boys help boys RayeGong • 2 days ago • Lastly replied by magic1187 | 2 |
 |
local.ai
Livid PRO |
567 |
 |
公司本地部署开源模型 majuzhang • 5h 29m ago • Lastly replied by cherylaskinnero6 | 67 |
 |
本地部署小模型(100G 上下显存可用) 用于 Verilog 生成 or 自动化验证的可行性 anyinuo0413 • 6h 37m ago • Lastly replied by ChinaCN | 5 |
 |
如何在公司放台设备跑模型? JohnXu20151211 • 3 days ago • Lastly replied by JohnXu20151211 | 22 |
 |
V2EX 提供的 deepseek v4 flash，好好好快， fly gebiwanger • 4 days ago • Lastly replied by xiaoshouchen | 1 |
 |
local.ai 接力，老爷们 lllll rrZ2C • 4 days ago • Lastly replied by RayeGong | 21 |
 |
我接力一下 local.ai lihawhaw • 4 days ago • Lastly replied by RayeGong | 14 |
 |
接力我的 local.ai raslan • 4 days ago • Lastly replied by RayeGong | 6 |
 |
local.ai 求接力，前 5 位有打赏 jtam • 4 days ago • Lastly replied by RayeGong | 19 |
Select Language