Model benchmarks
unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL local LLM performance
As of August 2026, unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL runs at up to 179.3 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
30B
Peak speed
179.3 tok/s
Average speed
169.2 tok/s
Min memory
14.6 GB
Max context
65,536 tokens
Avg output / run
52,001 tokens
Avg runtime / run
4m 44s
Avg quality
76.8
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 | 76.3 | 76.8 | 77.4 |
| Agent Workflow | 77.7 | 83.0 | 88.2 |
| Code Generation | 62.1 | 63.8 | 65.4 |
| Role Play & Narrative | 71.7 | 79.3 | 87.0 |
| Research & Analysis | 79.8 | 81.3 | 82.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 3080 Ti | llama.cpp | Q4_K | 179.3 tok/s | 169.2 tok/s | 14.6 GB | 65,536 tokens | 76.8 | 2 |
Frequently asked questions
- Is unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL good for coding?
- In our benchmarks, unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL scores 63.8/100 for coding. It runs at about 169.2 tok/s, so if you want more speed, Gemma4:E2B/QAT-MTP@131K is faster (~303.9 tok/s) and still scores well for coding (66.9/100).
- How fast is unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL for local inference?
- Across 2 community benchmark runs, unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL reaches up to 179.3 tok/s and averages 169.2 tok/s, with the fastest results on NVIDIA GeForce RTX 3080 Ti.
- How much memory does unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL need?
- The leanest observed configuration used about 14.6 GB of memory (quantizations tested: Q4_K).
- Which tools have been used to run unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.