Model benchmarks
NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL local LLM performance
As of October 2026, NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL runs at up to 47.8 tok/s for local inference (best of 5 community benchmark runs across 1 GPU).
Model size
4B
Peak speed
47.8 tok/s
Average speed
46.9 tok/s
Avg PP
889.3 tok/s
Min memory
4.5 GB
Max context
32,768 tokens
Avg output / run
7,596 tokens
Avg runtime / run
2m 47s
Avg quality
70.4
Benchmark runs
5
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 5 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 | 67.5 | 70.4 | 72.7 |
| Agent Workflow | 81.1 | 85.9 | 89.7 |
| Code Generation | 56.3 | 61.2 | 65.2 |
| Role Play & Narrative | 70.4 | 73.8 | 79.1 |
| Research & Analysis | 54.4 | 60.6 | 65.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL 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 | 47.8 tok/s | 46.9 tok/s | 4.5 GB | 32,768 tokens | 70.4 | 5 |
Benchmark runs
All 5 NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL 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 good for coding?
- In our benchmarks, NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL scores 61.2/100 for coding. It runs at about 46.9 tok/s, so if you want more speed, nvidia/Qwen3.8-27B-NVFP4 is faster (~63.3 tok/s) and still scores well for coding (82.7/100).
- Is NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL good for agentic (tool-using) tasks?
- In our benchmarks, NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL scores 85.9/100 for agentic workflows. It runs at about 46.9 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 for local inference?
- Across 5 community benchmark runs, NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL reaches up to 47.8 tok/s and averages 46.9 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 need?
- The leanest observed configuration used about 4.5 GB of memory (quantizations tested: Q4_K).
- Which tools have been used to run NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.