Model benchmarks
Nemotron-3.5-Lightning_t1p95k40m05 local LLM performance
As of November 2026, Nemotron-3.5-Lightning_t1p95k40m05 runs at up to 125.8 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
30B
Peak speed
125.8 tok/s
Average speed
125.7 tok/s
Avg PP
1133.0 tok/s
Min memory
44.7 GB
Max context
32,768 tokens
Avg output / run
28,813 tokens
Avg runtime / run
3m 54s
Avg quality
75.6
Benchmark runs
2
GPUs tested
1
Quality by task
Average LLM-judged quality (0–100) with the run-to-run spread shown as a P5–P95 band, overall and for each benchmark task, across all 2 runs. The low and high columns show how much the judge’s score varies between runs, and need at least two runs to display.
| Task | P5 (low) | Avg | P95 (high) |
|---|---|---|---|
| Overall | 75.5 | 75.6 | 75.6 |
| Agent Workflow | 85.9 | 88.4 | 90.8 |
| Code Generation | 60.7 | 64.4 | 68.0 |
| Role Play & Narrative | 72.2 | 76.0 | 79.7 |
| Research & Analysis | 70.9 | 73.6 | 76.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination Nemotron-3.5-Lightning_t1p95k40m05 has been benchmarked on, ranked by peak token generation speed. Last updated November 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Tesla V100-PCIE-32GB | llama.cpp | — | 125.8 tok/s | 125.7 tok/s | 44.7 GB | 32,768 tokens | 75.6 | 2 |
Benchmark runs
All 2 Nemotron-3.5-Lightning_t1p95k40m05 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Nemotron-3.5-Lightning_t1p95k40m05 good for coding?
- In our benchmarks, Nemotron-3.5-Lightning_t1p95k40m05 scores 64.4/100 for coding. It runs at about 125.7 tok/s, so if you want more speed, Qwen3.6-35B-A3B-Q4_K_XL is faster (~156.9 tok/s) and still scores well for coding (82.2/100).
- Is Nemotron-3.5-Lightning_t1p95k40m05 good for agentic (tool-using) tasks?
- In our benchmarks, Nemotron-3.5-Lightning_t1p95k40m05 scores 88.4/100 for agentic workflows. It runs at about 125.7 tok/s, so if you want more speed, swift-1.5-qwen3.8-flash-next-iq3_s is faster (~259.0 tok/s) and still scores well for agentic workflows (88.9/100).
- How fast is Nemotron-3.5-Lightning_t1p95k40m05 for local inference?
- Across 2 community benchmark runs, Nemotron-3.5-Lightning_t1p95k40m05 reaches up to 125.8 tok/s and averages 125.7 tok/s, with the fastest results on Tesla V100-PCIE-32GB.
- How much memory does Nemotron-3.5-Lightning_t1p95k40m05 need?
- The leanest observed configuration used about 44.7 GB of memory.
- Which tools have been used to run Nemotron-3.5-Lightning_t1p95k40m05?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.