Apple M5 Max Mac Studio
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 1
- Three Used V100 GPUs Reach 100.8 Tokens/s With Qwen 3.6 35B
A homelab builder measured 100.8 tokens per second for Qwen 3.6 35B at Q8 on three used Nvidia V100 GPUs with a 4K context, falling to 72.7 tokens per second at 128K. Across more than 130 llama.cpp tests, the dense Qwen 3.6 27B managed 24.3 tokens per second at 4K. In the reported 128K run, the three-V100 build consumed about half the GPU energy of the three-P100 setup. The listed $1,042 price covers only the GPUs and selected components, excluding RAM, storage, the case, cooling, and one of the two CPUs.
Tom’s Hardware · 🔥 0
Experience and discussion from the community
Share my Apple M5 Max Mac Studio experienceAsk about Apple M5 Max Mac Studio
Nobody has shared their experience with Apple M5 Max Mac Studio yet.