Model benchmarks
Inkling-2-Mini-oQ4e-mtp local LLM performance
As of November 2026, Inkling-2-Mini-oQ4e-mtp runs at up to 59.6 tok/s for local inference (best of 6 community benchmark runs across 1 GPU).
Model size
1.6B
Peak speed
59.6 tok/s
Average speed
57.4 tok/s
Avg PP
862.7 tok/s
Min memory
16.2 GB
Max context
262,144 tokens
Avg output / run
42,808 tokens
Avg runtime / run
12m 24s
Avg quality
79.5
Benchmark runs
6
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 6 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 | 62.2 | 79.5 | 88.6 |
| Agent Workflow | 10.7 | 65.8 | 93.2 |
| Code Generation | 78.7 | 83.2 | 88.1 |
| Role Play & Narrative | 68.7 | 82.1 | 91.3 |
| Research & Analysis | 83.1 | 86.9 | 89.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination Inkling-2-Mini-oQ4e-mtp 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 |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Max | oMLX | oQ4e | 59.6 tok/s | 57.4 tok/s | 16.2 GB | 262,144 tokens | 79.5 | 6 |
Benchmark runs
All 6 Inkling-2-Mini-oQ4e-mtp runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Inkling-2-Mini-oQ4e-mtp good for coding?
- In our benchmarks, Inkling-2-Mini-oQ4e-mtp scores 83.1/100 for coding. It runs at about 57.4 tok/s, so if you want more speed, qwen3.8-27b-Swift1.5-Uncensored-ATX-AI3 is faster (~85.5 tok/s) and still scores well for coding (84.8/100).
- Is Inkling-2-Mini-oQ4e-mtp good for agentic (tool-using) tasks?
- In our benchmarks, Inkling-2-Mini-oQ4e-mtp scores 65.8/100 for agentic workflows. It runs at about 57.4 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 Inkling-2-Mini-oQ4e-mtp for local inference?
- Across 6 community benchmark runs, Inkling-2-Mini-oQ4e-mtp reaches up to 59.6 tok/s and averages 57.4 tok/s, with the fastest results on Apple M5 Max.
- How much memory does Inkling-2-Mini-oQ4e-mtp need?
- The leanest observed configuration used about 16.2 GB of memory (quantizations tested: oQ4e).
- Which tools have been used to run Inkling-2-Mini-oQ4e-mtp?
- Benchmarks were submitted using oMLX. Results are community-contributed and updated as new runs arrive.