DGX Spark vs M5 Max 128GB
For running local LLMs · 8 reports across 5 models
Tokens per second by model
| Model | DGX Spark | M5 Max 128GB |
|---|---|---|
| Gemma 4up to 31B | — | 7.5n=3 |
| Qwen3.6up to 35B | — | 5.5n=2 |
| DeepSeek V3 | —n=1 | — |
| GLM-5.1 | —n=1 | — |
| Qwen3.5up to 122B | — | —n=1 |
For running local LLMs · 8 reports across 5 models
| Model | DGX Spark | M5 Max 128GB |
|---|---|---|
| Gemma 4up to 31B | — | 7.5n=3 |
| Qwen3.6up to 35B | — | 5.5n=2 |
| DeepSeek V3 | —n=1 | — |
| GLM-5.1 | —n=1 | — |
| Qwen3.5up to 122B | — | —n=1 |