Model benchmarks
apodex_Apodex-1.1-mini-IQ2_M local LLM performance
As of October 2026, apodex_Apodex-1.1-mini-IQ2_M runs at up to 103.1 tok/s for local inference (best of 4 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
103.1 tok/s
Average speed
94.3 tok/s
Avg PP
909.8 tok/s
Min memory
16.2 GB
Max context
262,144 tokens
Avg output / run
18,748 tokens
Avg runtime / run
3m 24s
Avg quality
65.9
Benchmark runs
4
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 4 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 | 54.7 | 65.9 | 78.4 |
| Agent Workflow | 22.6 | 55.2 | 81.8 |
| Code Generation | 44.2 | 58.8 | 70.2 |
| Role Play & Narrative | 69.8 | 76.7 | 85.2 |
| Research & Analysis | 63.3 | 72.8 | 81.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination apodex_Apodex-1.1-mini-IQ2_M 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 5060 | llama.cpp | — | 103.1 tok/s | 94.3 tok/s | 16.2 GB | 262,144 tokens | 65.9 | 4 |
Benchmark runs
All 4 apodex_Apodex-1.1-mini-IQ2_M runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is apodex_Apodex-1.1-mini-IQ2_M good for agentic (tool-using) tasks?
- In our benchmarks, apodex_Apodex-1.1-mini-IQ2_M scores 55.2/100 for agentic workflows. It runs at about 94.3 tok/s, so if you want more speed, cyber-tiel-coder-35b-a3b-mtp is faster (~115.9 tok/s) and still scores well for agentic workflows (86.4/100).
- How fast is apodex_Apodex-1.1-mini-IQ2_M for local inference?
- Across 4 community benchmark runs, apodex_Apodex-1.1-mini-IQ2_M reaches up to 103.1 tok/s and averages 94.3 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does apodex_Apodex-1.1-mini-IQ2_M need?
- The leanest observed configuration used about 16.2 GB of memory.
- Which tools have been used to run apodex_Apodex-1.1-mini-IQ2_M?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.