The fleet
Every machine that has produced a benchmark run. This page is generated from the result files, so it reflects exactly what has been tested — not what I intend to test.
NVIDIA DGX Spark (GB10)
| Accelerator | NVIDIA GB10 |
| Unified memory | 122 GB |
| System RAM | 122 GB |
| Models tested | Qwen/Qwen3.6-27B, Qwen/Qwen3.6-35B-A3B, Qwen/Qwen3.8-27B, Qwen/Qwen3.8-Flash-Next, deepseek-ai/DeepSeek-V4-Flash, meta-models/Muse-Glimmer-30B, nvidia/Nemotron-3.5-Lightning-30B-A3B, openai/gpt-oss-120b |
| Runs recorded | 39 |