LLM Inference Benchmark Explorer

Qwen3.8-Flash-Next on RTX PRO 6000 — NVFP4, SGLang, TP1, speculative decoding k=3 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelQwen3.8-Flash-Next
Parameters176B
Intelligence Index39.8
Agentic Index53.6
DeviceRTX PRO 6000
QuantizationNVFP4
Max C16
Chat Capacity64
Agentic Capacity24
TP—
DP—
PP—
EngineSGLang
Speculative DecodingYes
CTTFT (ms)TPS (tok/s)Status
1139155.77PASS
2196119.96PASS
422190.76PASS
825263.69PASS
1625743.19PASS
32322322.19FAIL

In OpenZeka's measurement, Qwen3.8-Flash-Next (176B parameters), served in NVFP4 format with SGLang and speculative decoding on RTX PRO 6000, reached a generation speed of 155.8 tok/s per request and a time to first token (TTFT) of 139 ms with a single request.

Considering the speed targets alone (the KV cache limit was not calculated for this configuration), the estimated capacity is 64 users for chat use and 24 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) in pinned host RAM. mem-frac 0.96, max 16 running; C=32 queues.

Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.