 |
2 台 DGX Spark 上运行的本地 LLM 横向对比 ldm0 • 1 day ago • Lastly replied by ldm0 | 27 |
 |
pro6000 部署 Qwen 3.8 flash next nvfp4 zzutmebwd • 1 day ago • Lastly replied by coefu | 23 |
 |
qwen3.8 本机部署后搭配什么搜索工具呢？ idblife • 2 days ago • Lastly replied by wises | 19 |
 |
mac 本地部署 llm 不是最佳选择 Need4more • 3 days ago • Lastly replied by winson030 | 89 |
 |
DeepSeek-V4-Flash-Vision-Exp 权重开源了，原生视觉集成
TGOcc PRO |
4 |
 |
大模型 LLM 是怎么实现计算的？还是内部调用了工具？ jacketma • 4 days ago • Lastly replied by CasualYours | 15 |
 |
mac m5 ultra 上线中国官网。1.2T 显存带宽， 256GB 版本 8.6 万 sentinelK • Aug 28 • Lastly replied by sadan9 | 51 |
 |
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 • 16h 25m ago • Lastly replied by turing518 | 18 |
 |
mac ultra deepseek harness & qwen3.8-27B 几点经验 coefu • 1 day ago • Lastly replied by yachen | 13 |
 |
自己攒了个 comfyui 交流社区 nicolaszhao4 • 2 days ago • Lastly replied by nicolaszhao4 | 18 |
 |
m1max 64g+1T 满 GPU 的 MacBook Pro 适合部署哪个本地模型 l764191074537 • 3 days ago • Lastly replied by maybestone | 9 |
 |
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 • Aug 27 • Lastly replied by msg7086 | 66 |
|
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 • Aug 26 • Lastly replied by tgfbeta | 55 |
 |
local.ai 接力是干嘛呀？ justmiho • Aug 19 • 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 • Aug 19 • Lastly replied by coefu | 13 |
 |
一个 15MB Rust 二进制文件的 Agent CLI，零运行时依赖，旨在充分发挥任何模型的性能 Koimiao • 1 day ago • Lastly replied by rev1si0n | 8 |
 |
local.ai 接力， boys help boys RayeGong • Aug 19 • Lastly replied by magic1187 | 2 |
 |
local.ai
Livid PRO |
567 |
Select Language