NVIDIA Nemotron 3.5 Bolt 74B-A9B on TensorFold, one Spark
1× DGX Spark · TensorFold ·
Tested configuration
- Hardware
- 1x NVIDIA DGX Spark (128GB)
- Serving runtime
- TensorFold
- Runtime version or build
- tensorfold-native with the recipe's Bolt lane backend (libbolt), built locally from the recipe's pinned TensorFold reference and patch set
- Weight quantization or precision
- IQ2_XXS experts, NVFP4 Mamba projections, and Q8_0 attention, latent, and head projections
- Benchmark date
- Recipe credit
- MiaAI-Lab Nemotron 3.5 Bolt TensorFold recipeBy MiaAI-Lab
6f61d7727ae3fac010f30e240799cc884d295f6e
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 | 79.23 | 0.44 |
| 2 | 106.59 | 0.44 |
| 4 | 149.49 | 0.64 |
| 8 | 180.56 | 0.92 |
| 12 | 205.05 | 5.12 |
| 16 | 234.45 | 2.49 |
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/s | TTFT p95 (s) |
|---|---|---|
| 4,096 input tokens | 1,150.46 | 2.70 |
| 32,768 input tokens | 1,421.49 | 22.09 |
| 131,072 input tokens | 1,076.89 | 120.84 |
| 245,760 input tokensPasskey prompt | 829.93 | 294.65 |
Sustained load
20-minute soak at concurrency 8 · ~1024 input / 512 output tokens per request.
- Aggregate throughput
- 145.52 output tok/s
- TTFT p95
- 2.30 s
- Completed requests
- 345
- 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
- 90.3 / 100
- Pass@3 · passed at least once
- 85.5%
- Pass³ · passed every trial
- 85.5%