Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

M5 Ultra Mac Studio beats a single GB10 in agentic test but trails a Spark pair

AI summary

Tom's Hardware benchmarked an M5 Ultra Mac Studio with a 36-core CPU, 80-core GPU and up to 512GB of unified memory against a single Dell Pro Precision GB10 system, which it described as nearly identical to an Nvidia DGX Spark. Using llama.cpp with Qwen 3.8 27B and its native multi-token prediction, the Mac completed the Artificial Analysis AgentPerf-Local test in just under half the time of the GB10 system. The report also cited 1.2 TB/s of memory bandwidth for the Mac versus 273 GB/s for the GB10. For DeepSeek V4.1 Flash 1017, however, the Mac's llama.cpp setup took 10–25 minutes for the longest tested contexts, while a two-Spark cluster using DSpark speculative decoding and TensorFold took under five minutes. The report said Mac Studio lead times stretched into February 2027.

In-depth insight

The tested Mac configuration cost about $12,300, while two Spark systems with 4TB drives were described as costing roughly $15,000–$20,000 or more. The results indicate that the Mac offered stronger raw specifications and won the agentic benchmark against one Spark-like system, but the Nvidia cluster had advantages in large-model inference software, model compatibility and support.

Apple’s updated Mac Studio with the M5 Ultra SoC has already proven itself as one of the most powerful systems around, thanks to its 36-core CPU and 80-core GPU with Neural Accelerators for the matrix math operations that drive AI compute. Beyond that raw power, options for up to 512GB of unified memory have many local AI enthusiasts lining up for the 13 to 15 weeks it’ll take for Apple to ship one right now.

But is our tested Mac Studio config worth a whopping $12,300 or more for those folks? We already tested the maxed-out M5 Ultra chip with the popular Qwen 3.8 27B in our initial review, but that compact dense model doesn’t come anywhere close to exercising 256GB of memory. We wanted to fill that pool to the brim with cutting-edge large models like DeepSeek V4.1 Flash 1017 and GLM 5.3 Flash.

We also have some new benchmarks at our disposal to see how the Mac Studio stacks up in agentic tasks on the GPU side in the wake of our review of the Microsoft Surface Laptop Ultra with Nvidia’s RTX Spark chip. So there's much to dig into.

#Apple#Nvidia#Mac Studio#M5 Ultra#Dell Pro Precision GB10#DGX Spark#DeepSeek V4.1 Flash 1017#GLM 5.3 Flash#Qwen 3.8 27B#llama.cpp#MLX#TensorFold

Original · 10 min readRead the original
Group chat

No comments yet. Start the conversation.