Overview
Local language models compared: knowledge, math, code and German, plus speed. Each model variant is shown with its most recent completed run. How the numbers are measured is described under Methodology.
Suite v2b · profile quick
| Model | Overall | Knowledge & reasoning | Math | Instruction following | Code | German | gen t/s | pp t/s 4k | TTFT 4k ms | Date |
|---|---|---|---|---|---|---|---|---|---|---|
|
gpt-oss-120b
MXFP4 · Reasoning on · direct · NVIDIA DGX Spark, 128 GB RAM
|
73.1 | 68.5 | 70.4 | 66.1 | 83.0 | 77.4 | – | – | – | 2026-09-18 |
|
qwen3.8-flash-next-ple4
NVFP4 · Reasoning off · direct · NVIDIA DGX Spark, 128 GB RAM
|
71.5 | 77.9 | 73.2 | 49.6 | 75.5 | 81.1 | 26 | 2041 | 1974 | 2026-09-17 |
|
gemma-4-12b-it
Q8 · Reasoning off · direct · NVIDIA DGX Spark, 128 GB RAM
|
65.8 | 67.5 | 60.8 | 51.3 | 75.0 | 74.5 | 17 | 1359 | 2952 | 2026-09-18 |
|
gemma-4-12b-it-heretic
Q8 · Reasoning off · direct · NVIDIA DGX Spark, 128 GB RAM
|
65.8 | 68.4 | 59.2 | 50.0 | 75.0 | 76.5 | 17 | 1358 | 2954 | 2026-09-19 |
|
qwen3.8-27b-mtp
NVFP4 · Reasoning off · direct · NVIDIA DGX Spark, 128 GB RAM
|
64.2 | 69.9 | 60.4 | 49.5 | 65.0 | 76.3 | 15 | 2551 | 1578 | 2026-09-18 |
|
qwen3.8-27b-abliterated
NVFP4 · Reasoning off · direct · NVIDIA DGX Spark, 128 GB RAM
|
61.4 | 71.5 | 58.0 | 46.1 | 59.5 | 72.1 | 16 | 2472 | 1628 | 2026-09-20 |
|
gemma-4-12b-it-heretic
NVFP4 · Reasoning off · direct · NVIDIA DGX Spark, 128 GB RAM
|
57.7 | 63.7 | 48.4 | 46.8 | 62.0 | 67.7 | 21 | 5258 | 763 | 2026-09-18 |
|
nemotron-3.5-lightning-dspark
NVFP4 · Reasoning off · direct · NVIDIA DGX Spark, 128 GB RAM
|
53.1 | 55.8 | 40.4 | 46.0 | 53.0 | 70.5 | 84 | 7237 | 554 | 2026-09-17 |
|
qwen3.5-9b-heretic-v2-mtp
NVFP4 · Reasoning off · direct · NVIDIA DGX Spark, 128 GB RAM
|
51.7 | 65.1 | 35.6 | 44.1 | 46.5 | 67.0 | 32 | 6291 | 640 | 2026-09-18 |
Scores run from 0 to 100; the best value per category is shown in bold. Hovering a category cell lists its tasks with standard error (±) and number of items (n). Speed: generation in tokens/s, prompt processing at 4k context in tokens/s, time to first token at 4k context in ms. Click a column header to sort.