The same QuietBox 2 and DGX Spark (alone and as a pair), reinstalled with Talos Linux and serving the same model builds as Kubernetes pods, against the Ubuntu runs on the main page. Each Talos test is paired with the identical Ubuntu test. Median change in throughput from Ubuntu: —.
← Best Personal AI Hardware Image generation Paired data (CSV) Code and data on GitHub
Each dot is one test (a workload at one user count); the bar is the model's median.
Each dot is one model at one user count; the bar is the median for that system.
Percent change from Ubuntu to Talos. Columns are workloads, split by the number of concurrent users.
tt serve and Docker on Ubuntu. The Spark ran the same vLLM image, by digest, everywhere.pci=pcie_bus_safe: without it the
ConnectX-7 runs with a 128-byte PCIe payload and one rail tops out near 97 Gb/s instead of about 110 Gb/s.
The vLLM image's CUDA forward-compat libraries are loaded ahead of the host's 595 driver libraries; without
them NCCL crashes at startup on this image. Two models so far, gpt-oss-120b and Qwen3.5-122B-A10B;
Llama 3.3 70B has not been run on the pair under Talos.