LLM Inference Benchmark Explorer
DeepSeek V4 Flash 0731 on 4× DGX Spark — NVFP4, vLLM, TP4 inference benchmark
Open this configuration in the LLM Inference Benchmark Explorer
| Model | DeepSeek V4 Flash 0731 |
|---|---|
| Parameters | 304B |
| Intelligence Index | 34.3 |
| Agentic Index | 41 |
| Device | 4× DGX Spark |
| Quantization | NVFP4 |
| Max C | 1+ |
| Chat Capacity | 4+ |
| Agentic Capacity | 1+ |
| TP | 4 |
| DP | — |
| PP | — |
| Engine | vLLM |
| Speculative Decoding | — |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 256 | 69.50 | PASS |
In OpenZeka's measurement, DeepSeek V4 Flash 0731 (304B parameters), served in NVFP4 format with vLLM on 4× DGX Spark (TP=4), reached a generation speed of 69.5 tok/s per request and a time to first token (TTFT) of 256 ms with a single request.
Considering the speed targets and the available KV cache capacity, the estimated capacity is at least 4 users for chat use and at least 1 for agentic use. The realistic capacity will likely fall between these two values. In scenarios dominated by coding, tool use, long workflows and multi-agent use, capacity approaches the agentic estimate; where shorter interactions, standard conversations and lighter tasks dominate, it approaches the chat estimate.
“At least” means the configuration met the speed targets even at the highest load tested, so the real capacity may be higher.
This configuration was measured with a single request only, so the estimate rests on one measurement.
Notes: TP=4. Single C=1 test (scaling comparison). Best C=1 TPS for this model.
Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.
In OpenZeka's measurement, DeepSeek V4 Flash 0731 (304B parameters), served in NVFP4 format with vLLM on 4× DGX Spark (TP=4), reached a generation speed of 69.5 tok/s per request and a time to first token (TTFT) of 256 ms with a single request.
Considering the speed targets and the available KV cache capacity, the estimated capacity is at least 4 users for chat use and at least 1 for agentic use. The realistic capacity will likely fall between these two values. In scenarios dominated by coding, tool use, long workflows and multi-agent use, capacity approaches the agentic estimate; where shorter interactions, standard conversations and lighter tasks dominate, it approaches the chat estimate.
“At least” means the configuration met the speed targets even at the highest load tested, so the real capacity may be higher.
This configuration was measured with a single request only, so the estimate rests on one measurement.