LLM Inference Benchmark Explorer
Gemma-4-31B-it on 2× DGX Spark — NVFP4, vLLM, TP2 inference benchmark
Open this configuration in the LLM Inference Benchmark Explorer
| Model | Gemma-4-31B-it |
|---|---|
| Parameters | 31B |
| Intelligence Index | 19 |
| Agentic Index | 4.2 |
| Device | 2× DGX Spark |
| Quantization | NVFP4 |
| Max C | 0 |
| Chat Capacity | 0 |
| Agentic Capacity | 0 |
| TP | 2 |
| DP | — |
| PP | — |
| Engine | vLLM |
| Speculative Decoding | — |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 136 | 19.42 | FAIL |
| 2 | 227 | 19.59 | FAIL |
| 4 | 246 | 19.17 | FAIL |
| 8 | 280 | 18.20 | FAIL |
| 16 | 293 | 15.81 | FAIL |
| 32 | 337 | 13.21 | FAIL |
| 64 | 420 | 9.16 | FAIL |
In OpenZeka's measurement, Gemma-4-31B-it (31B parameters), served in NVFP4 format with vLLM on 2× DGX Spark (TP=2), reached a generation speed of 19.4 tok/s per request and a time to first token (TTFT) of 136 ms with a single request.
At the default speed targets (at least 20 tok/s per request, TTFT at most 1,000 ms) there is no capacity estimate for this configuration: no measured load level met them.
Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.
In OpenZeka's measurement, Gemma-4-31B-it (31B parameters), served in NVFP4 format with vLLM on 2× DGX Spark (TP=2), reached a generation speed of 19.4 tok/s per request and a time to first token (TTFT) of 136 ms with a single request.
At the default speed targets (at least 20 tok/s per request, TTFT at most 1,000 ms) there is no capacity estimate for this configuration: no measured load level met them.