DGX Spark vs RX 9070
For running local LLMs · 3 reports across 3 models
Tokens per second by model
| Model | DGX Spark | RX 9070 |
|---|---|---|
| DeepSeek V3 | —n=1 | — |
| GLM-5.1 | —n=1 | — |
| Qwen3.6up to 35B | — | 46.9n=1 |
For running local LLMs · 3 reports across 3 models
| Model | DGX Spark | RX 9070 |
|---|---|---|
| DeepSeek V3 | —n=1 | — |
| GLM-5.1 | —n=1 | — |
| Qwen3.6up to 35B | — | 46.9n=1 |