M5 Ultra vs. DGX Spark: Local Compute Benchmarks
nickbaumann_ · x · 2026-08-26
Comparison of M5 Ultra Mac Studio (512GB), 4x DGX Spark, and 4x AMD Ryzen AI Halo (all priced $15-20k):
- Compute: Spark is fastest; 200GbE interconnects combine compute effectively. Mac is quick on normal prompts but slower on long ones. Halos suffer from 10GbE bottlenecks, performing worse than the Mac.
- Bandwidth: Mac's 512GB unified bus delivers 4x the tokens/sec of Spark/Halo, which are bottlenecked by sequential token passing across boxes.
- Power: Mac consumes less power than a gaming PC.
Related event: M5 Ultra Mac Studio Sparks Debate Over Local AI Compute Economics(9 posts)→
More from Infra
- Autonomous sells personal AI computers from $26,100 that keep data in the room — dee_hw · 2026-10-15
- vLLM's bitwise-consistent RL: zero KL on Nemotron NVFP4, 91.3% throughput on DeepSeek-V4-Flash — DynamicWebPaige · 2026-10-15
- vLLM achieves bitwise-consistent RL training: DeepSeek-V4-Flash hits 0 diff over 100 steps — vllm_project · 2026-10-15
- vLLM Achieves Bitwise-Consistent RL Training, Fixing KL Blowups and Score Collapse — vllm_project · 2026-10-15
- Analyst Ben Bajarin: The AI Industry Needs a Lot More Compute — BenBajarin · 2026-10-15
- Next-gen GraalVM benchmarks: 4x faster startup, 2x less memory, no build step needed — RealGeneKim · 2026-10-15