Spark Bench

Qwen3.8-Flash-Next FP4-Local QAD on TensorFold v1.1.4, one Spark, 262K

1× DGX Spark · TensorFold ·

Tested configuration

Hardware
1x NVIDIA DGX Spark (128GB)
Serving runtime
TensorFold
Runtime version or build
TensorFold v1.1.4 (eab85828) with the recipe's patches 0001-0017
Weight quantization or precision
FP4-Local QAD
Benchmark date
Recipe credit
MiaAI-Lab Qwen3.8 Flash Next single-Spark TensorFold recipeBy MiaAI-Lab20e15e41f2f514a0d287710f4665ee1b5009ba41

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)
141.540.35
283.180.42
4111.730.97
898.6419.84
1295.1544.68
1688.2369.13

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 tokens1,281.741.95
32,768 input tokens2,059.5014.30
131,072 input tokens2,066.3962.05
245,760 input tokensPasskey prompt1,936.59126.64

Sustained load

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

Aggregate throughput
77.79 output tok/s
TTFT p95
32.12 s
Completed requests
189
Request errors
0

Serving regression checks 13/13 passed

Tool-use evaluation

Complete · 100% completionSafety 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
89.0 / 100
Pass@3 · passed at least once
84.1%
Pass³ · passed every trial
84.1%

Read the tool-eval report and scenario findings

Other configurations for Qwen3.8-Flash-Next NVFP4