mirror of
https://github.com/deepseek-ai/DeepSeek-R1.git
synced 2026-11-05 00:47:42 +00:00
[GH-ISSUE #276] 我想问本地部署deepseek-r1:671b,大概需要多少算力? #210
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-R1#210
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @king121456 on GitHub (Feb 5, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/276
@darktown52 commented on GitHub (Feb 5, 2025):
性能优势
数学与代码: R1 本地部署后,可极致发挥其 MATH-500(97.3)、Codeforces(2029)等垂直领域优势,远超网页端 V3。
中文场景: C-Eval 91.8 vs V3 的 86.5,中文专业问答更精准。
长上下文支持: 128K 上下文本地处理,适合长文档分析、代码库理解。
功能限制
多模态支持: R1 未提及图像/语音处理能力,与网页端 V3 一致,仅限文本任务。
实时更新: 本地模型版本固定,需手动更新;网页端可能持续迭代(如知识库更新至最新)。
部署成本与隐私
硬件需求: 需 8×A100 GPU,显存 300GB+,成本较高;网页端零硬件投入。
隐私控制: 本地数据完全隔离,适合医疗、金融等敏感领域;网页端依赖云端传输。
@ACautomata commented on GitHub (Feb 5, 2025):
https://snowkylin.github.io/blogs/a-note-on-deepseek-r1.html
approximately 158GB
@xueshuai0922 commented on GitHub (Feb 7, 2025):
这个是动态量化后的,如果完整部署,得需要多少显存
@cgf120 commented on GitHub (Feb 9, 2025):
671*4 = fp32
@yahiko-l commented on GitHub (Feb 16, 2025):
你要部署671B,那个1400GB文件大小那个,你大约需要20张A800
@raineverknow commented on GitHub (Feb 17, 2025):
不是,按照fp8去部署,就是650G左右大小
@sxk000 commented on GitHub (Feb 18, 2025):
fp8的你实际部署过吗?有显存占用截图吗?用的什么卡?
@Harrison-cc commented on GitHub (Feb 21, 2025):
腾讯云一键部署, FP8部署, 8 卡 H20, 大概用了 700 多 G 显存
@Dragode commented on GitHub (Feb 24, 2025):
请问 8 卡 H20 部署后,性能是什么表现?比如在16并发下,ttft 和 吞吐量 的指标如何?
@Harrison-cc commented on GitHub (Feb 25, 2025):
压测下来最大并发 8, 输入 16k 长度下, ttft=4s
@easyzhang0315 commented on GitHub (Mar 1, 2025):
2 * H800 * 8(BF8)。 或 4 * A800 * 8 (BF16)
@king121456 commented on GitHub (Mar 3, 2025):
生产环境都是用vllm部署的吗?
@github-actions[bot] commented on GitHub (May 7, 2025):
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!
@github-actions[bot] commented on GitHub (May 31, 2025):
false