Qwen3.6-35B-A3B NVFP4 (Unsloth): vLLM GB10 + MiaAI-Lab patch, MTP 2, one Spark, 262K, thinking off
1× DGX Spark · vLLM ·
Tested configuration
- Hardware
- 1x NVIDIA DGX Spark (128GB)
- Serving runtime
- vLLM
- Runtime version or build
- vLLM 0.26.1.dev0+g568afb3a1 with FlashInfer 0.6.14, built locally from timothystewart6/vllm-gb10 @ 94352d3 with its pinned versions
- Weight quantization or precision
- NVFP4
- Benchmark date
- Recipe credit
- MiaAI-Lab Unsloth Qwen3.6-35B NVFP4 DGX Spark recipeBy MiaAI-Lab
79c9e6f359f6101cdacd0dfd6fe9861ae2493a4d
Decode sweep
~256 input / 512 output tokens per request. Output throughput is aggregate across concurrent requests. TTFT means time to first token.
| Concurrency | Output tok/s | TTFT p95 (s) |
|---|---|---|
| 1 | 77.46 | 0.20 |
| 2 | 114.90 | 1.33 |
| 4 | 190.66 | 0.35 |
| 8 | 306.34 | 1.24 |
| 12 | 343.87 | 0.67 |
| 16 | 429.21 | 0.95 |
Prefill and context
- Configured request window
- 262,144 tokens
- Longest tested prompt
- 131,072 target input tokens
- Validated retrieval
- UnavailablePasskey not run
Input throughput uses full request wall time. The passkey measures retrieval from one long prompt.
| Workload (c1) | Input tok/s | TTFT p95 (s) |
|---|---|---|
| 4,096 input tokens | 2,710.94 | 0.65 |
| 32,768 input tokens | 3,711.67 | 8.49 |
| 131,072 input tokens | 2,429.77 | 53.44 |
Sustained load
20-minute soak at concurrency 8 · ~1024 input / 512 output tokens per request.
- Aggregate throughput
- 286.66 output tok/s
- TTFT p95
- 0.52 s
- Completed requests
- 678
- Request errors
- 0
Serving regression checks 12/12 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
- 88.3 / 100
- Pass@3 · passed at least once
- 89.9%
- Pass³ · passed every trial
- 76.8%