Model benchmarks
NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 local LLM performance
As of October 2026, NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 runs at up to 65.6 tok/s for local inference (best of 10 community benchmark runs across 1 GPU).
Model size
4B
Peak speed
65.6 tok/s
Average speed
61.1 tok/s
Avg PP
903.1 tok/s
Min memory
5.6 GB
Max context
32,768 tokens
Avg output / run
7,364 tokens
Avg runtime / run
1m 52s
Avg quality
69.0
Benchmark runs
10
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 10 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 | 65.7 | 69.0 | 74.4 |
| Agent Workflow | 72.0 | 77.8 | 87.4 |
| Code Generation | 57.0 | 63.0 | 70.7 |
| Role Play & Narrative | 64.4 | 75.3 | 85.2 |
| Research & Analysis | 53.2 | 60.0 | 68.6 |
Performance by hardware and tool
Every hardware/tool/quantization combination NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 has been benchmarked on, ranked by peak token generation speed. Last updated October 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 4060 Laptop GPU | llama.cpp | Q4_K | 65.6 tok/s | 61.1 tok/s | 5.6 GB | 32,768 tokens | 69.0 | 10 |
Benchmark runs
All 10 NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 good for coding?
- In our benchmarks, NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 scores 63.0/100 for coding. It runs at about 61.1 tok/s, so if you want more speed, Nex-N2.5-mini-IQ3_XXS is faster (~91.4 tok/s) and still scores well for coding (81.6/100).
- Is NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 good for agentic (tool-using) tasks?
- In our benchmarks, NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 scores 77.8/100 for agentic workflows. It runs at about 61.1 tok/s, so if you want more speed, Nex-N2.5-mini-APEX-Mini is faster (~88.2 tok/s) and still scores well for agentic workflows (91.3/100).
- How fast is NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 for local inference?
- Across 10 community benchmark runs, NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 reaches up to 65.6 tok/s and averages 61.1 tok/s, with the fastest results on NVIDIA GeForce RTX 4060 Laptop GPU.
- How much memory does NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4 need?
- The leanest observed configuration used about 5.6 GB of memory (quantizations tested: Q4_K).
- Which tools have been used to run NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.