Spark Bench

Qwen3.8-Flash-Next FP4-Local (NVIDIA QAD) on TensorFold, one Spark, thinking off

1× DGX Spark · TensorFold ·

Tested configuration

Hardware
1x NVIDIA DGX Spark (128GB)
Serving runtime
TensorFold
Runtime version or build
TensorFold db281878ddb8 (zig-flashnext) with the recipe's patches 0001-0015 (patch hash c0a2df4c680d). It was built locally with PULL=0 on nvcr.io/nvidia/pytorch:26.07-py3 and the recipe's sha256-checked Zig 0.17.0 toolchain, as image tag tensorfold-qwen38:zig-db28187
Weight quantization or precision
FP4-Local
Benchmark date
Recipe credit
MiaAI-Lab Qwen3.8 Flash Next single-Spark TensorFold recipeBy MiaAI-Lab656879fd752749bbd11a6e1a065a326c00940911

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)
134.290.48
257.620.64
475.710.51
889.3020.46
12100.4341.47
1695.6961.00

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 tokens1,176.041.95
32,768 input tokens1,962.3715.03
131,072 input tokens1,956.2965.10
245,760 input tokensPasskey prompt1,827.36133.79

Sustained load

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

Aggregate throughput
85.72 output tok/s
TTFT p95
28.44 s
Completed requests
207
Request errors
0

Serving regression checks 13/13 passed

Tool-use evaluation

Incomplete pilot · 98.6% completionSafety gate passed

Comparisons require complete results with 100% completion under the same protocol ID. This run is retained as individual evidence.

Protocol ID
tool-eval-standard-v1-b60e2f0
Workload
69 mock-tool scenarios per trial · 3 trials
Mean score
86.0 / 100
Pass@3 · passed at least once
76.5%
Pass³ · passed every trial
76.5%

Read the tool-eval report and scenario findings

Other configurations for Qwen3.8-Flash-Next NVFP4