LLM Inference Benchmark Explorer
Qwen3.8-Flash-Next on 1× DGX Spark — NVFP4, SGLang, TP1, speculative decoding k=3 inference benchmark
Open this configuration in the LLM Inference Benchmark Explorer
| Model | Qwen3.8-Flash-Next |
|---|---|
| Parameters | 176B |
| Intelligence Index | 39.8 |
| Agentic Index | 53.6 |
| Device | 1× DGX Spark |
| Quantization | NVFP4 |
| Max C | 2 |
| Chat Capacity | 8 |
| Agentic Capacity | 3 |
| TP | — |
| DP | — |
| PP | — |
| Engine | SGLang |
| Speculative Decoding | Yes |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 302 | 28.50 | PASS |
| 2 | 393 | 23.61 | PASS |
| 4 | 566 | 17.13 | FAIL |
| 8 | 763 | 11.80 | FAIL |
In OpenZeka's measurement, Qwen3.8-Flash-Next (176B parameters), served in NVFP4 format with SGLang and speculative decoding on 1× DGX Spark, reached a generation speed of 28.5 tok/s per request and a time to first token (TTFT) of 302 ms with a single request.
Considering the speed targets alone (the KV cache limit was not calculated for this configuration), 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: NEXTN MTP k=3. PLE N-gram table (47.7 GiB) file-backed on NVMe. mem-frac 0.85, max 8 running.
Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.
In OpenZeka's measurement, Qwen3.8-Flash-Next (176B parameters), served in NVFP4 format with SGLang and speculative decoding on 1× DGX Spark, reached a generation speed of 28.5 tok/s per request and a time to first token (TTFT) of 302 ms with a single request.
Considering the speed targets alone (the KV cache limit was not calculated for this configuration), 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.