Spark Bench

Qwen3.8-Flash-Next NVIDIA NVFP4 on vLLM 0.34.0, two Sparks

2× DGX Spark · vLLM 0.34.0 ·

Single-stream decode
44.35 output tok/s
Time to first token · p95, c1
0.36 s
Tool eval completeSafety gate failed

This configuration failed a critical tool-use check. Review the findings before using it for consequential automation. See the tool evaluation

Tested configuration

Hardware
2x NVIDIA DGX Spark (128GB each)
Serving runtime
vLLM 0.34.0
Runtime version or build
stock vLLM 0.34.0, ARM64, CUDA 13.0.2. · docker.io/vllm/vllm-openai@sha256:e40eb98263fa13418dda684147d73e8ec4a2b0e056a37e955dc189cd1b11dd16.
Weight quantization or precision
NVIDIA ModelOpt NVFP4 with mixed precision for the other layers.
Benchmark date
Recipe credit
MiaAI-Lab dual-Spark topologyBy MiaAI-Labcd839d0b62f6c737178a0c2037733420e0524ebf

Decode sweep

~256 input / 512 output tokens per request. Output throughput is aggregate across concurrent requests. TTFT means time to first token.

ConcurrencyOutput tok/sTTFT p95 (s)
144.350.36
267.310.65
4103.830.81
8102.9223.26
1298.5343.55
16101.8963.01

Prefill and context

Configured request window
262,144 tokens
Longest tested prompt
245,760 target input tokens
Validated retrieval
≈240K input tokens · passkey passed

Input throughput uses full request wall time. The passkey measures retrieval from one long prompt.

Workload (c1)Input tok/sTTFT p95 (s)
4,096 input tokens1,084.292.06
32,768 input tokens2,311.4215.28
131,072 input tokens2,071.3673.17
245,760 input tokensPasskey prompt2,439.8099.43

Sustained load

20-minute soak at concurrency 8 · ~1024 input / 512 output tokens per request.

Aggregate throughput
140.54 output tok/s
TTFT p95
19.13 s
Completed requests
335
Request errors
0

Serving regression checks 13/13 passed

Tool-use evaluation

Complete · 100% completion Safety gate failed

Compare only against complete results with 100% completion under the same protocol ID.

Protocol ID
tool-eval-standard-v1-b60e2f0
Workload
69 mock-tool scenarios per trial · 3 trials
Mean score
92.0 / 100
Pass@3 · passed at least once
97.1%
Pass³ · passed every trial
84.1%

Read the tool-eval report and scenario findings

Other configurations for Qwen3.8-Flash-Next NVFP4

Install model

Copy this prompt and paste it into an AI assistant with access to your DGX Spark.