Model benchmarks
NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16 local LLM performance
As of October 2026, NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16 runs at up to 63.5 tok/s for local inference (best of 5 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
63.5 tok/s
Average speed
61.2 tok/s
Avg PP
769.9 tok/s
Min memory
6.4 GB
Max context
32,768 tokens
Avg output / run
7,472 tokens
Avg runtime / run
1m 55s
Avg quality
72.2
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 | 70.6 | 72.2 | 74.5 |
| Agent Workflow | 71.6 | 77.2 | 84.5 |
| Code Generation | 62.1 | 65.9 | 72.2 |
| Role Play & Narrative | 76.1 | 80.5 | 83.5 |
| Research & Analysis | 54.8 | 65.1 | 71.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16 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 | Q6_K | 63.5 tok/s | 61.2 tok/s | 6.4 GB | 32,768 tokens | 72.2 | 5 |
Benchmark runs
All 5 NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16 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-Q6_K-DFLASH-BF16 good for coding?
- In our benchmarks, NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16 scores 65.9/100 for coding. It runs at about 61.2 tok/s, so if you want more speed, Ornith-1.5-35B-A3B.APEX-I-NanoPlus is faster (~110.5 tok/s) and still scores well for coding (81.1/100).
- Is NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16 good for agentic (tool-using) tasks?
- In our benchmarks, NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16 scores 77.2/100 for agentic workflows. It runs at about 61.2 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-Q6_K-DFLASH-BF16 for local inference?
- Across 5 community benchmark runs, NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16 reaches up to 63.5 tok/s and averages 61.2 tok/s, with the fastest results on NVIDIA GeForce RTX 4060 Laptop GPU.
- How much memory does NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16 need?
- The leanest observed configuration used about 6.4 GB of memory (quantizations tested: Q6_K).
- Which tools have been used to run NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.