niklaslenzWhat to run on 128 GB
One small desk box with 128 GB of shared memory. 1 complete run on 1× DGX Spark (GB10). Click any number for the raw output. Click a column to sort.
1 complete run
| # | Creator | Setup | Overallof 100 | Agent testbrowser check | Speedtok/s | Qualitymean of 7 tests | Memorylargest context |
|---|---|---|---|---|---|---|---|
| 1 |  Mia's AI Lab | Qwen3.8-Flash-Nextnew1× DGX Spark | 92.3 of 100rank 1 of 1as of 20 Oct 2026 |  8.5 / 10 | 42.8≈ 16.9 s for 500 wordscode 43.2 · prose 42.5 | 67.1%mean of 7 tests | 256Ktokens tested |
Creator: who made the recipe; the picture leads to their profile. Overall: 0 to 100 from speed (45 %), quality (30 %), the browser check (5 %) and my rating (20 %); the run with the highest score is rank 1. The score shows the date of the newest measurement in the class. Scores are relative to the best run in the class today; a better model later moves older runs down. How the score is made. Agent test: the model builds one 3D scene as an agent, one attempt, no help; a browser checks the page, 0 to 10 points. Speed: tokens per second with one request, thinking off. Quality: the mean of 7 tests (MMLU-Pro, GPQA, IFEval, LiveCodeBench, long text 8K and 32K, GPQA with thinking), each with its 95 % margin of error on the recipe page. Memory: the largest context that loaded and answered. All other numbers (each quality test, time, peak memory, sparkDash, engine, quant) are on the recipe page. Only a run with every part done and independently checked is listed. Click a row for the recipe, the exact command and the raw files.