Model benchmarks
maritaca-ai_S5-nano-Q4_K_M local LLM performance
As of November 2026, maritaca-ai_S5-nano-Q4_K_M runs at up to 98.2 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
98.2 tok/s
Average speed
85.2 tok/s
Avg PP
1325.5 tok/s
Min memory
5.3 GB
Max context
32,768 tokens
Avg output / run
36,240 tokens
Avg runtime / run
8m 12s
Avg quality
59.6
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 | 56.7 | 59.6 | 62.5 |
| Agent Workflow | 76.5 | 79.7 | 82.9 |
| Code Generation | 1.5 | 1.7 | 1.8 |
| Role Play & Narrative | 77.6 | 77.8 | 78.0 |
| Research & Analysis | 71.1 | 79.3 | 87.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination maritaca-ai_S5-nano-Q4_K_M 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 GeForce RTX 3060 | llama.cpp | Q4_K_M | 98.2 tok/s | 85.2 tok/s | 5.3 GB | 32,768 tokens | 59.6 | 2 |
Benchmark runs
All 2 maritaca-ai_S5-nano-Q4_K_M runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is maritaca-ai_S5-nano-Q4_K_M good for agentic (tool-using) tasks?
- In our benchmarks, maritaca-ai_S5-nano-Q4_K_M scores 79.7/100 for agentic workflows. It runs at about 85.2 tok/s, so if you want more speed, qwen3.8-flash-next-iq3_s is faster (~98.3 tok/s) and still scores well for agentic workflows (89.9/100).
- How fast is maritaca-ai_S5-nano-Q4_K_M for local inference?
- Across 2 community benchmark runs, maritaca-ai_S5-nano-Q4_K_M reaches up to 98.2 tok/s and averages 85.2 tok/s, with the fastest results on NVIDIA GeForce RTX 3060.
- How much memory does maritaca-ai_S5-nano-Q4_K_M need?
- The leanest observed configuration used about 5.3 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run maritaca-ai_S5-nano-Q4_K_M?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.