Model benchmarks
Nex-N2.5-mini-APEX-Mini local LLM performance
As of September 2026, Nex-N2.5-mini-APEX-Mini runs at up to 89.6 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
89.6 tok/s
Average speed
88.2 tok/s
Avg PP
924.3 tok/s
Min memory
16.0 GB
Max context
131,072 tokens
Avg output / run
32,777 tokens
Avg runtime / run
6m 22s
Avg quality
81.1
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 | 76.6 | 81.1 | 85.5 |
| Agent Workflow | 90.4 | 91.3 | 92.2 |
| Code Generation | 54.5 | 65.8 | 77.1 |
| Role Play & Narrative | 83.7 | 85.8 | 87.9 |
| Research & Analysis | 78.0 | 81.4 | 84.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination Nex-N2.5-mini-APEX-Mini has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 5060 | llama.cpp | — | 89.6 tok/s | 88.2 tok/s | 16.0 GB | 131,072 tokens | 81.1 | 2 |
Benchmark runs
All 2 Nex-N2.5-mini-APEX-Mini runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Nex-N2.5-mini-APEX-Mini good for coding?
- In our benchmarks, Nex-N2.5-mini-APEX-Mini scores 65.8/100 for coding. It runs at about 88.2 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-MLX-oQ4e is faster (~107.9 tok/s) and still scores well for coding (81.5/100).
- Is Nex-N2.5-mini-APEX-Mini good for agentic (tool-using) tasks?
- In our benchmarks, Nex-N2.5-mini-APEX-Mini scores 91.3/100 for agentic workflows, among the top 2 for agentic workflows on consumer hardware (≤24 GB VRAM). It runs at about 88.2 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-MLX-oQ4e-MTP is faster (~123.7 tok/s) and still scores well for agentic workflows (84.4/100).
- How fast is Nex-N2.5-mini-APEX-Mini for local inference?
- Across 2 community benchmark runs, Nex-N2.5-mini-APEX-Mini reaches up to 89.6 tok/s and averages 88.2 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does Nex-N2.5-mini-APEX-Mini need?
- The leanest observed configuration used about 16.0 GB of memory.
- Which tools have been used to run Nex-N2.5-mini-APEX-Mini?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.