Model benchmarks
nemotron-3.5-bolt local LLM performance
As of October 2026, nemotron-3.5-bolt runs at up to 116.6 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
3.5B
Peak speed
116.6 tok/s
Average speed
105.7 tok/s
Avg PP
2374.0 tok/s
Min memory
n/a
Max context
8,192 tokens
Avg output / run
6,769 tokens
Avg runtime / run
56s
Avg quality
72.2
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 | 68.3 | 72.2 | 76.1 |
| Agent Workflow | 76.7 | 80.4 | 84.2 |
| Code Generation | 36.0 | 53.4 | 70.7 |
| Role Play & Narrative | 76.4 | 77.5 | 78.5 |
| Research & Analysis | 76.5 | 77.4 | 78.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination nemotron-3.5-bolt 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 |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon AI PRO R9700 | Strata | — | 116.6 tok/s | 105.7 tok/s | n/a | 8,192 tokens | 72.2 | 2 |
Benchmark runs
All 2 nemotron-3.5-bolt runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is nemotron-3.5-bolt good for coding?
- In our benchmarks, nemotron-3.5-bolt scores 53.4/100 for coding. It runs at about 105.7 tok/s, so if you want more speed, Qwen3.6-35B-A3B-Q4_K_XL is faster (~156.9 tok/s) and still scores well for coding (82.2/100).
- Is nemotron-3.5-bolt good for agentic (tool-using) tasks?
- In our benchmarks, nemotron-3.5-bolt scores 80.4/100 for agentic workflows. It runs at about 105.7 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-Q4_K_S is faster (~162.4 tok/s) and still scores well for agentic workflows (87.8/100).
- How fast is nemotron-3.5-bolt for local inference?
- Across 2 community benchmark runs, nemotron-3.5-bolt reaches up to 116.6 tok/s and averages 105.7 tok/s, with the fastest results on AMD Radeon AI PRO R9700.
- Which tools have been used to run nemotron-3.5-bolt?
- Benchmarks were submitted using Strata. Results are community-contributed and updated as new runs arrive.