A100 80GB vs DGX Spark
For running local LLMs · 26 reports across 9 models
Highest reported generation speed by model family
These maxima come from different community setups. Model size, quantization, GPU count, offloading and concurrency may differ. They do not establish which GPU is faster for the same workload. Check the comparison conditions →
| Model | A100 80GB | DGX Spark |
|---|---|---|
| DeepSeek V4 Flashup to 285B | — | 90.0n=10 |
| Qwen3.8up to 2400B | 56.8n=1 | 181.0n=4 |
| Ling-3.0up to 124B | — | 40.9n=4 |
| GLM-5.2up to 744B | — | 24.0n=2 |
| DeepSeek V3 | — | —n=1 |
| GLM-5.1 | — | —n=1 |
| Kimi K3 | — | 20.0n=1 |
| Museup to 30B | — | 37.0n=1 |
| Qwen3.6up to 35B | — | —n=1 |