DeepSeek V4 Flash DSpark: original July deployment, two Sparks (TP=2), thinking off
2× DGX Spark · vLLM (Anemll DSpark) ·
Tested configuration
- Hardware
- 2x NVIDIA DGX Spark (128GB each)
- Serving runtime
- vLLM (Anemll DSpark)
- Runtime version or build
- the prebuilt ghcr.io/anemll/dspark-vllm-gx10:0.1.1 image (image ID 3430d6614a8e, repo digest sha256:a83948492cf13df455170fb42885f5ef4db54fefe0feff0f841ecbff464ac9d8, the same digest on both nodes). It was already present locally from the original deployment
- Weight quantization or precision
- Unavailable
- Benchmark date
- Recipe credit
- MiaAI-Lab DeepSeek-v4-Flash DSpark 2x DGX Spark recipeBy MiaAI-Lab
b4cc551b0adb6aa62979d92686b9fe0f1326d640
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 | 42.12 | 4.12 |
| 2 | 67.92 | 0.83 |
| 4 | 81.94 | 9.80 |
| 8 | 92.52 | 28.08 |
| 12 | 99.21 | 35.92 |
| 16 | 104.82 | 55.35 |
Prefill and context
- Configured request window
- 1,048,576 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/s | TTFT p95 (s) |
|---|---|---|
| 4,096 input tokens | 1,014.62 | 2.42 |
| 32,768 input tokens | 1,304.90 | 30.62 |
| 131,072 input tokens | 1,132.52 | 116.92 |
| 245,760 input tokensPasskey prompt | 1,400.67 | 175.40 |
Sustained load
20-minute soak at concurrency 8 · ~1024 input / 512 output tokens per request.
- Aggregate throughput
- 111.10 output tok/s
- TTFT p95
- 20.24 s
- Completed requests
- 266
- Request errors
- 0
Serving regression checks 13/13 passed
Tool-use evaluation
Complete · 100% completionSafety gate passed
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
- 84.1%
- Pass³ · passed every trial
- 78.3%