超10万,两台Mac Studio在家就能跑满血DeepSeek,网友:这是性价比最高的大模型一体机

VIP超10万,两台Mac Studio在家就能跑满血DeepSeek,网友:这是性价比最高的大模型一体机
在AI计算领域,没有比这更强的个人电脑了。这要从它的架构说起。对于那些有本地部署满血版DeepSeek需求的用户,目前建议的配置是选购512GB统一内存 + 1TB SSD,搭载M3 Ultra芯片的Mac Studio,官网售价74249元,可以叠加国补、教育优惠、12期分期等,这可能是目前门槛最低、性价比最高的满血版DeepSeek本地部署方案。对于企业而言,尽管Mac Studio确实可以部署6000亿参数的大模型,但在内存带宽、模型精调服务等方面,跟专用的大模型一体机仍有差距,采购需要谨慎评估。
开通可读全文 ·1.9k 人阅读
最低0.47元/天 解锁文章

苹果新款Mac Studio的发布在AI领域掀起了波澜。这款配备了号称地表最强的全新M3 Ultra和M4 Max芯片的电脑,凭借其强大的性能,引发了AI爱好者和专业人士的广泛关注。尤其是M3 Ultra芯片加持下的Mac Studio,最高可配备32核CPU和80核GPU,并支持高达512GB的统一内存,更是成为了焦点中的焦点。

 

 

有专门在各种设备上尝试跑大模型的机构深入分析显示,这款设备能够运行超6000亿参数的LLM(大语言模型)。这意味着个人用户在家就能流畅运行完整体量的DeepSeek R1,这一突破让众多AI爱好者兴奋不已。与M1 Ultra、M2 Ultra类似,全新的M3 Ultra实际上是由两颗M3 Max处理器通过台积电的先进封装技术(苹果将其称为“UltraFusion”)拼接在一起的。苹果表示,这使得M3 Ultra相比M2 Ultra性能提升50%,相比初代M1 Ultra提升80%。再加上M3 Ultra额外的GPU核心,其图形处理性能大约是M2 Ultra的两倍。搭载M3 Ultra芯片的Mac Studio最低配置96GB的统一内存,最高可选配至512GB,达到个人电脑迄今统一内存配置之最。凭借800GB/s的内存带宽,在家跑类似DeepSeek R1这样的模型完全可行(至少在4-bit精度下)。

 

国外一家专注于在不同设备上运行大模型的EXO Labs在X平台表示,两台配备512GB内存(总价18,000美元)的M3 Ultra Mac Studio,通过Thunderbolt 5连接后,可以以20 tokens/秒的速度运行满血的DeepSeek R1(8-bit)。512GB版M3 Ultra Mac Studio非常适合运行超大规模的稀疏MoE(专家混合)模型,比如DeepSeek V3/R1。如果你想在家运行完整、未量化的DeepSeek R1,只需要两台512GB版M3 Ultra Mac

VIP 两台Mac Studio跑满血DeepSeek:671B大模型私有化部署全记录 大模型推理的落地瓶颈往往不在算力,而在内存容量与带宽。以671B参数的满血DeepSeek为例,仅模型权重就需要数百GB存储,传统GPU方案成本高企,而Apple统一内存架构让Mac Studio能以较低成本提供超大内存与高带宽。借助MLX分布式推理,双机协同可将模型层拆分到两台设备并行计算,通过万兆网络同步张量,实现接近数据中心级别的私有化推理。该方案适合数据敏感、需要深度定制模型行为的开发者,并能无缝接入OpenAI兼容工具链,作为团队内部的“大模型一体机”使用。两台M2 Ultra 192GB机型的实 开通可读全文·303 阅读·0 点赞·3 收藏 阅读全文

相关推荐

从“能用”到“好用”:Mac Studio M4 48G环境下Ollama模型优化完全指南

本文针对Mac Studio M4 48G环境下运行Ollama模型的内存优化问题,提供了系统解决方案。通过量化策略选择(推荐Q4_K_M)、上下文长度调优(建议8192起)和批处理尺寸控制,可稳定运行14B模型。对于32B模型,则需结合GPU层数分配和MLX加速技术。文中包含详细的内存估算公式、配置示例和性能数据,帮助用户从"能用"到"好用"地部署大语言模型。

AI的内部世界的博客 431

【飞控】MATLAB中UAV Toolbox Support Package for PX4 Autopilots和Pixhawk Pilot Support Package (PSP) 的关系?

区分UAV Toolbox Support Package for PX4 Autopilots和Pixhawk Pilot Support Package (PSP)

m0_58373406的博客 745

SAP-PP MD04详解一

MD04是SAP运行MRP后的结果查询事务码,其他功能强大,标准功能比如:查询/更改物料主数据、转换计划订单到生产订单/采购申请、查询/更改各个MRP元素对应的单据等等。而且还可以附加标准的菜单或者自定义添加事务码上去。老铁将做一个MD04详细说明系列,本篇为第一篇之MRP元素说明。 我们来看看MD04基本界面 可以看到主要的数据显示界面,有日期、MRP元素、MRP元素数据、再计划日期、收货/需求、可用数量、工厂、库存地点等栏位。光标定位到MRP元素列,按F1即可看到各类MRP元素的说...

weixin_52158549的博客 1万+

别再手动搬数据了!用rclone一键同步MinIO到华为云OBS的保姆级教程

本文详细介绍了如何使用rclone工具实现MinIO到华为云OBS的数据迁移,包括环境准备、双端配置、迁移前验证、实战迁移及后期监控等步骤。通过rclone的增量同步、断点续传等功能,确保数据迁移高效安全,特别适合需要跨云存储迁移的用户。

weixin_30839881的博客 531

【车载以太网】ATU(Address Translation Unit / Address Table Unit)

【车载以太网】ATU(Address Translation Unit / Address Table Unit)

天赐好车的博客 162

YOLO26 实战全流程:从数据集标注到端到端无NMS推理(完整版,附ProgLoss核心调参技巧+避坑指南)

本章节是实战经验的精华❌ 数据集标注不规范,导致模型精度低 → ✅ 严格遵守工业级标注规范,标注框紧贴目标边缘,不要漏标/多标;❌ 训练时未使用预训练权重,导致收敛极慢 → ✅ 必须开启,预训练权重能让模型快速收敛;❌ ProgLoss参数调整幅度过大,导致训练崩溃 → ✅ 每次只调整一个参数,幅度±0.02即可,循序渐进;❌ 推理时强行添加NMS参数,画蛇添足 → ✅ YOLO26无需NMS,推理命令中不要加conf/iou参数,否则会降低推理速度;

专注于Python爬虫开发,分享爬虫技巧、项目实战与反爬经验,使用Scrapy、BeautifulSoup等工具,解决数据抓取难题。 1142

解锁VS2022!手把手教你本地部署Deepseek

在 VS2022 中本地部署 Deepseek,我们首先需要确保硬件资源的充足,如高性能的 GPU、大容量内存和高速存储等,这是模型稳定运行的基石。如果生成的摘要能够准确概括原文的核心内容,就表明 Deepseek 模型在文本分析方面的功能正常,部署稳定可靠。这对于开发者来说,能够大大提高开发效率,当遇到一些常见的功能实现时,可以借助 Deepseek 模型快速生成基础代码框架,减少手动编写的工作量。在大语言模型的蓬勃发展的当下,Deepseek 凭借其卓越的性能和创新的技术,已然成为该领域的佼佼者。

远程部署调试 运行安装 项目调试 二次开发 项目技术新 持续迭代 部分源码免费分享 1万+

国产麒麟V10系统命令大全,100个实用命令助你玩转系统!

国产麒麟V10系统命令大全,100个实用命令助你玩转系统!

网络技术联盟站 1918

20、机器人硬件改造与Geomagic Touch设备的运动学和动力学模型

本文详细介绍了机器人CRS 465和255的硬件改造过程,包括数字阶段、模拟阶段、功率阶段及软件实现,并深入研究了Geomagic Touch触觉设备的五自由度与三自由度运动学、微分运动学及动力学模型。文章还探讨了其在虚拟手术、装配等场景中的应用,提出了硬件与模型优化方向,如电源管理改进、信号处理优化、参数校准与自适应控制,并展望了多机器人协作、多传感器融合与智能控制算法的发展前景。

e4f5g6h7的博客 126

jdk-8u144-linux-x64.tar.gz.

该资源为搭建Linux系统Java环境用,资源的后缀为tar.gz格式的压缩包

大中型超市收银系统(可直接运行)

光步前台收银系统系统功能:商品销售、商品退货、挂单、收银员权限、会员销售、单品取消、整单取消、商品查询、脱机销售、脱机数据上传,基本资料下载,开钱箱、小票打印、收款结算,支持多币种付款方式(现金、储值卡、礼券、微信等),支持多种促销。运行环境:.net 4.0登陆信息用户名:1001 密码:123456内置商品信息,商品编码可输入00001000 - 00010000,测试效果相关功能键F5 结算 F9挂单 F11商品查询 F8退货 Insert单品取消 Del整单取消 F12开钱箱F2 会员 Ctrl+Z退出系统 Home 锁屏 相关源码待公开

深度学习工具包 DeepLearningToolbox

深度学习工具包Deprecation notice.-----This toolbox is outdated and no longer maintained.There are much better tools available for deep learning than this toolbox, e.g. [Theano](http://deeplearning.net/software/theano/), [torch](http://torch.ch/) or [tensorflow](http://www.tensorflow.org/)I would suggest you use one of the tools mentioned above rather than use this toolbox.Best, Rasmus.DeepLearnToolbox================A Matlab toolbox for Deep Learning.Deep Learning is a new subfield of machine learning that focuses on learning deep hierarchical models of data.It is inspired by the human brain's apparent deep (layered, hierarchical) architecture.A good overview of the theory of Deep Learning theory is[Learning Deep Architectures for AI](http://www.iro.umontreal.ca/~bengioy/papers/ftml_book.pdf)For a more informal introduction, see the following videos by Geoffrey Hinton and Andrew Ng.* [The Next Generation of Neural Networks](http://www.youtube.com/watch?v=AyzOUbkUf3M) (Hinton, 2007)* [Recent Developments in Deep Learning](http://www.youtube.com/watch?v=VdIURAu1-aU) (Hinton, 2010)* [Unsupervised Feature Learning and Deep Learning](http://www.youtube.com/watch?v=ZmNOAtZIgIk) (Ng, 2011)If you use this toolbox in your research please cite [Prediction as a candidate for learning deep hierarchical models of data](http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=6284)```@MASTERSTHESIS\{IMM2012-06284, author = "R. B. Palm", title = "Prediction as a candidate for learning deep hierarchical models of data", year = "2012",}```Contact: rasmusbergpalm at gmail dot comDirectories included in the toolbox-----------------------------------`NN/` - A library for Feedforward Backpropagation Neural Networks`CNN/` - A library for Convolutional Neural Networks`DBN/` - A library for Deep Belief Networks`SAE/` - A library for Stacked Auto-Encoders`CAE/` - A library for Convolutional Auto-Encoders`util/` - Utility functions used by the libraries`data/` - Data used by the examples`tests/` - unit tests to verify toolbox is workingFor references on each library check REFS.mdSetup-----1. Download.2. addpath(genpath('DeepLearnToolbox'));Example: Deep Belief Network---------------------```matlabfunction test_example_DBNload mnist_uint8;train_x = double(train_x) / 255;test_x = double(test_x) / 255;train_y = double(train_y);test_y = double(test_y);%% ex1 train a 100 hidden unit RBM and visualize its weightsrand('state',0)dbn.sizes = [100];opts.numepochs = 1;opts.batchsize = 100;opts.momentum = 0;opts.alpha = 1;dbn = dbnsetup(dbn, train_x, opts);dbn = dbntrain(dbn, train_x, opts);figure; visualize(dbn.rbm{1}.W'); % Visualize the RBM weights%% ex2 train a 100-100 hidden unit DBN and use its weights to initialize a NNrand('state',0)%train dbndbn.sizes = [100 100];opts.numepochs = 1;opts.batchsize = 100;opts.momentum = 0;opts.alpha = 1;dbn = dbnsetup(dbn, train_x, opts);dbn = dbntrain(dbn, train_x, opts);%unfold dbn to nnnn = dbnunfoldtonn(dbn, 10);nn.activation_function = 'sigm';%train nnopts.numepochs = 1;opts.batchsize = 100;nn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.10, 'Too big error');```Example: Stacked Auto-Encoders---------------------```matlabfunction test_example_SAEload mnist_uint8;train_x = double(train_x)/255;test_x = double(test_x)/255;train_y = double(train_y);test_y = double(test_y);%% ex1 train a 100 hidden unit SDAE and use it to initialize a FFNN% Setup and train a stacked denoising autoencoder (SDAE)rand('state',0)sae = saesetup([784 100]);sae.ae{1}.activation_function = 'sigm';sae.ae{1}.learningRate = 1;sae.ae{1}.inputZeroMaskedFraction = 0.5;opts.numepochs = 1;opts.batchsize = 100;sae = saetrain(sae, train_x, opts);visualize(sae.ae{1}.W{1}(:,2:end)')% Use the SDAE to initialize a FFNNnn = nnsetup([784 100 10]);nn.activation_function = 'sigm';nn.learningRate = 1;nn.W{1} = sae.ae{1}.W{1};% Train the FFNNopts.numepochs = 1;opts.batchsize = 100;nn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.16, 'Too big error');```Example: Convolutional Neural Nets---------------------```matlabfunction test_example_CNNload mnist_uint8;train_x = double(reshape(train_x',28,28,60000))/255;test_x = double(reshape(test_x',28,28,10000))/255;train_y = double(train_y');test_y = double(test_y');%% ex1 Train a 6c-2s-12c-2s Convolutional neural network %will run 1 epoch in about 200 second and get around 11% error. %With 100 epochs you'll get around 1.2% errorrand('state',0)cnn.layers = { struct('type', 'i') %input layer struct('type', 'c', 'outputmaps', 6, 'kernelsize', 5) %convolution layer struct('type', 's', 'scale', 2) %sub sampling layer struct('type', 'c', 'outputmaps', 12, 'kernelsize', 5) %convolution layer struct('type', 's', 'scale', 2) %subsampling layer};cnn = cnnsetup(cnn, train_x, train_y);opts.alpha = 1;opts.batchsize = 50;opts.numepochs = 1;cnn = cnntrain(cnn, train_x, train_y, opts);[er, bad] = cnntest(cnn, test_x, test_y);%plot mean squared errorfigure; plot(cnn.rL);assert(er<0.12, 'Too big error');```Example: Neural Networks---------------------```matlabfunction test_example_NNload mnist_uint8;train_x = double(train_x) / 255;test_x = double(test_x) / 255;train_y = double(train_y);test_y = double(test_y);% normalize[train_x, mu, sigma] = zscore(train_x);test_x = normalize(test_x, mu, sigma);%% ex1 vanilla neural netrand('state',0)nn = nnsetup([784 100 10]);opts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samples[nn, L] = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.08, 'Too big error');%% ex2 neural net with L2 weight decayrand('state',0)nn = nnsetup([784 100 10]);nn.weightPenaltyL2 = 1e-4; % L2 weight decayopts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex3 neural net with dropoutrand('state',0)nn = nnsetup([784 100 10]);nn.dropoutFraction = 0.5; % Dropout fraction opts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex4 neural net with sigmoid activation functionrand('state',0)nn = nnsetup([784 100 10]);nn.activation_function = 'sigm'; % Sigmoid activation functionnn.learningRate = 1; % Sigm require a lower learning rateopts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex5 plotting functionalityrand('state',0)nn = nnsetup([784 20 10]);opts.numepochs = 5; % Number of full sweeps through datann.output = 'softmax'; % use softmax outputopts.batchsize = 1000; % Take a mean gradient step over this many samplesopts.plot = 1; % enable plottingnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex6 neural net with sigmoid activation and plotting of validation and training error% split training data into training and validation datavx = train_x(1:10000,:);tx = train_x(10001:end,:);vy = train_y(1:10000,:);ty = train_y(10001:end,:);rand('state',0)nn = nnsetup([784 20 10]); nn.output = 'softmax'; % use softmax outputopts.numepochs = 5; % Number of full sweeps through dataopts.batchsize = 1000; % Take a mean gradient step over this many samplesopts.plot = 1; % enable plottingnn = nntrain(nn, tx, ty, opts, vx, vy); % nntrain takes validation set as last two arguments (optionally)[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');```[![Bitdeli Badge](https://d2weczhvl823v0.cloudfront.net/rasmusbergpalm/deeplearntoolbox/trend.png)](https://bitdeli.com/free "Bitdeli Badge")

文档:亲测可用解决vnc灰屏,黑屏,鼠标大黑叉情况

主要解决vnc-viewer灰屏,黑屏,鼠标大黑叉等现象,详细见文档。

上一篇: 苹果iOS 18.4将强制升级HomeKit架构,旧版设备或无法使用
下一篇: 首款原生鸿蒙正式版手机下周发,余承东亲自官宣
佳晓晓
博客等级 码龄2年 976粉丝 133原创
评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付:10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值
⌂ 换网址