Model benchmarks
inkling-2-mini-64k local LLM performance
As of November 2026, inkling-2-mini-64k runs at up to 79.5 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
79.5 tok/s
Average speed
78.9 tok/s
Avg PP
504.6 tok/s
Min memory
10.7 GB
Max context
65,536 tokens
Avg output / run
36,634 tokens
Avg runtime / run
8m 39s
Avg quality
63.6
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 | 58.8 | 63.6 | 68.4 |
| Agent Workflow | 1.3 | 13.0 | 24.7 |
| Code Generation | 75.7 | 79.2 | 82.6 |
| Role Play & Narrative | 73.6 | 75.8 | 78.0 |
| Research & Analysis | 84.5 | 86.3 | 88.1 |
Performance by hardware and tool
Every hardware/tool/quantization combination inkling-2-mini-64k 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 3080 Ti | OpenAI-compatible | — | 79.5 tok/s | 78.9 tok/s | 10.7 GB | 65,536 tokens | 63.6 | 2 |
Benchmark runs
All 2 inkling-2-mini-64k runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is inkling-2-mini-64k good for coding?
- In our benchmarks, inkling-2-mini-64k scores 79.2/100 for coding. It runs at about 78.9 tok/s, so if you want more speed, ornith-1.5-35b-a3b-apex-mtp-i-quality is faster (~105.2 tok/s) and still scores well for coding (83.6/100).
- Is inkling-2-mini-64k good for agentic (tool-using) tasks?
- In our benchmarks, inkling-2-mini-64k scores 13.0/100 for agentic workflows. It runs at about 78.9 tok/s, so if you want more speed, ornith-1.5-35b-a3b-apex-mtp-quality is faster (~103.2 tok/s) and still scores well for agentic workflows (88.5/100).
- How fast is inkling-2-mini-64k for local inference?
- Across 2 community benchmark runs, inkling-2-mini-64k reaches up to 79.5 tok/s and averages 78.9 tok/s, with the fastest results on NVIDIA GeForce RTX 3080 Ti.
- How much memory does inkling-2-mini-64k need?
- The leanest observed configuration used about 10.7 GB of memory.
- Which tools have been used to run inkling-2-mini-64k?
- Benchmarks were submitted using OpenAI-compatible. Results are community-contributed and updated as new runs arrive.