LLM Inference Benchmark Explorer
Gemma-4-31B-it on 1× DGX Spark — NVFP4, vLLM, TP1 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 | 1× DGX Spark |
| Quantization | NVFP4 |
| Max C | 0 |
| Chat Capacity | 0 |
| Agentic Capacity | 0 |
| TP | — |
| DP | — |
| PP | — |
| Engine | vLLM |
| Speculative Decoding | — |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 202 | 10.81 | FAIL |
| 2 | 283 | 11.06 | FAIL |
| 4 | 294 | 10.89 | FAIL |
| 8 | 316 | 10.51 | FAIL |
| 16 | 347 | 10.04 | FAIL |
| 32 | 399 | 8.87 | FAIL |
| 64 | 532 | 7.36 | FAIL |
In OpenZeka's measurement, Gemma-4-31B-it (31B parameters), served in NVFP4 format with vLLM on 1× DGX Spark, reached a generation speed of 10.8 tok/s per request and a time to first token (TTFT) of 202 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.
Notes: Model: RedHatAI/gemma-4-31B-it-NVFP4 (31B dense)
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 1× DGX Spark, reached a generation speed of 10.8 tok/s per request and a time to first token (TTFT) of 202 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.