 |
q4 量化的大模型能比原版全精度的差多少？ jhytxy • Mar 6, 2025 • Lastly replied by mili100 | 2 |
 |
Intel GPU 的 llama-bench 测试结果 HojiOShi • Mar 5, 2025 |
 |
求 DeepSeekR1 性价比硬件推荐 v2er4241 • Mar 7, 2025 • Lastly replied by coala | 59 |
 |
咨询 GPU 服务器方案 MimicOctopus • Mar 5, 2025 • Lastly replied by tool2dx | 11 |
 |
大模型私有化是怎么集群部署的？ mingtdlb • Mar 4, 2025 • Lastly replied by volvo007 | 6 |
 |
ollama+docker 部署的 dify+ Linux 放在外网，如何设置才安全？ icemanpro • Mar 3, 2025 • Lastly replied by mmdsun | 9 |
 |
8 卡 H100 部署 DeepSeekR1 求助 zhyim • Mar 4, 2025 • Lastly replied by weiming | 15 |
 |
公司一个台式机想作为服务器部署本地大模型，怎么在局域网使用呢 xinhaiw • Mar 11, 2025 • Lastly replied by cander0815 | 21 |
 |
Thinkstation P8 搭配 4090 48G 测试 Deepseek-r1 devlnt • Feb 28, 2025 |
 |
8 路 L40 部署 R1-671B 上限是多少呢 jinja27 • Feb 24, 2025 • Lastly replied by jingzf0214 | 10 |
 |
LLM local 模型入门和使用 iv8d • Sep 7, 2025 • Lastly replied by miaoxiaomayi | 11 |
 |
有开源的可联网搜索的 ollama UI 项目推荐吗 goashore • Mar 1, 2025 • Lastly replied by coefuqin | 14 |
 |
DIFY 这类产品会成为主流吗，交互逻辑咋这么复杂，感觉没自己写代码方便 wushenlun • Feb 24, 2025 • Lastly replied by ericguo | 2 |
 |
各位大佬， m4mini32g 跑大模型🐂🍺还是 4060ti16g🐂🍺呀？ songche • Feb 18, 2025 • Lastly replied by chor02 | 22 |
 |
大佬们有没有基于大模型的推荐系统 demo spitfireuptown • Feb 17, 2025 • Lastly replied by murmur | 9 |
 |
ollama 如何手动下载模型？ mrleft • Feb 20, 2025 • Lastly replied by h4ckm310n | 15 |
 |
求助，做 AI 深度学习服务器跑大模型推理，选 RTX5080*2 还是一张 4090 duanrancosmos • Feb 14, 2025 • Lastly replied by Gnihton | 6 |
 |
Deepseek r1 14b 很有自己的想法 lostsquirrelX • Feb 13, 2025 • Lastly replied by lostsquirrelX | 2 |
 |
请问如何本地部署 AI 图片或视频清晰化功能? littlemis • Feb 10, 2025 • Lastly replied by tycholiu | 12 |
Select Language