Model benchmarks
nemotron-3.5-bolt:e4b local LLM performance
As of November 2026, nemotron-3.5-bolt:e4b runs at up to 85.7 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
7.5B
Peak speed
85.7 tok/s
Average speed
76.3 tok/s
Avg PP
1669.7 tok/s
Min memory
14.4 GB
Max context
65,536 tokens
Avg output / run
7,231 tokens
Avg runtime / run
1m 41s
Avg quality
65.1
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 | 64.4 | 65.1 | 65.8 |
| Agent Workflow | 64.5 | 70.2 | 75.9 |
| Code Generation | 53.4 | 59.5 | 65.5 |
| Role Play & Narrative | 65.7 | 67.8 | 70.0 |
| Research & Analysis | 58.3 | 62.9 | 67.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination nemotron-3.5-bolt:e4b 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA RTX 2000 Ada Generation Laptop GPU | Ollama | Q4_K_M | 85.7 tok/s | 76.3 tok/s | 14.4 GB | 65,536 tokens | 65.1 | 2 |
Benchmark runs
All 2 nemotron-3.5-bolt:e4b runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is nemotron-3.5-bolt:e4b good for coding?
- In our benchmarks, nemotron-3.5-bolt:e4b scores 59.5/100 for coding. It runs at about 76.3 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 nemotron-3.5-bolt:e4b good for agentic (tool-using) tasks?
- In our benchmarks, nemotron-3.5-bolt:e4b scores 70.2/100 for agentic workflows. It runs at about 76.3 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 nemotron-3.5-bolt:e4b for local inference?
- Across 2 community benchmark runs, nemotron-3.5-bolt:e4b reaches up to 85.7 tok/s and averages 76.3 tok/s, with the fastest results on NVIDIA RTX 2000 Ada Generation Laptop GPU.
- How much memory does nemotron-3.5-bolt:e4b need?
- The leanest observed configuration used about 14.4 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run nemotron-3.5-bolt:e4b?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.