LLM Inference Benchmark Explorer
DeepSeek-V4-Flash-Vision-Exp on 2× DGX Spark — FP8, vLLM, TP2, speculative decoding k=3 inference benchmark
Open this configuration in the LLM Inference Benchmark Explorer
| Model | DeepSeek-V4-Flash-Vision-Exp |
|---|---|
| Parameters | 305B |
| Intelligence Index | 34.8 |
| Agentic Index | 47.5 |
| Device | 2× DGX Spark |
| Quantization | FP8 |
| Max C | 2 |
| Chat Capacity | 8 |
| Agentic Capacity | 3 |
| TP | 2 |
| DP | — |
| PP | — |
| Engine | vLLM |
| Speculative Decoding | Yes |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 300 | 35.99 | PASS |
| 2 | 496 | 23.14 | PASS |
| 4 | 633 | 16.18 | FAIL |
| 8 | 908 | 8.75 | FAIL |
In OpenZeka's measurement, DeepSeek-V4-Flash-Vision-Exp (305B parameters), served in FP8 format with vLLM and speculative decoding on 2× DGX Spark (TP=2), reached a generation speed of 36 tok/s per request and a time to first token (TTFT) of 300 ms with a single request.
Considering the speed targets and the available KV cache capacity, the estimated capacity is 8 users for chat use and 3 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.
Notes: DSpark k=3, 131K context. Model: deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.
In OpenZeka's measurement, DeepSeek-V4-Flash-Vision-Exp (305B parameters), served in FP8 format with vLLM and speculative decoding on 2× DGX Spark (TP=2), reached a generation speed of 36 tok/s per request and a time to first token (TTFT) of 300 ms with a single request.
Considering the speed targets and the available KV cache capacity, the estimated capacity is 8 users for chat use and 3 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.