Model benchmarks
Inkling-2-Mini-UD-IQ3_XXS local LLM performance
As of November 2026, Inkling-2-Mini-UD-IQ3_XXS runs at up to 44.1 tok/s for local inference (best of 6 community benchmark runs across 0 GPUs).
Model size
Unknown
Peak speed
44.1 tok/s
Average speed
42.0 tok/s
Avg PP
708.1 tok/s
Min memory
13.0 GB
Max context
32,768 tokens
Avg output / run
12,207 tokens
Avg runtime / run
5m 7s
Avg quality
78.6
Benchmark runs
6
GPUs tested
0
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 | 68.5 | 78.6 | 84.7 |
| Agent Workflow | 30.2 | 68.2 | 84.3 |
| Code Generation | 72.5 | 74.9 | 77.2 |
| Role Play & Narrative | 73.9 | 85.2 | 91.5 |
| Research & Analysis | 82.3 | 85.8 | 89.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination Inkling-2-Mini-UD-IQ3_XXS 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 |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon Graphics | llama.cpp | — | 44.1 tok/s | 42.0 tok/s | 13.0 GB | 32,768 tokens | 78.6 | 6 |
Benchmark runs
All 6 Inkling-2-Mini-UD-IQ3_XXS runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Inkling-2-Mini-UD-IQ3_XXS good for coding?
- In our benchmarks, Inkling-2-Mini-UD-IQ3_XXS scores 74.9/100 for coding. It runs at about 42.0 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-UD-IQ3_XXS good for agentic (tool-using) tasks?
- In our benchmarks, Inkling-2-Mini-UD-IQ3_XXS scores 68.2/100 for agentic workflows. It runs at about 42.0 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-UD-IQ3_XXS for local inference?
- Across 6 community benchmark runs, Inkling-2-Mini-UD-IQ3_XXS reaches up to 44.1 tok/s and averages 42.0 tok/s, with the fastest results on AMD Radeon Graphics.
- How much memory does Inkling-2-Mini-UD-IQ3_XXS need?
- The leanest observed configuration used about 13.0 GB of memory.
- Which tools have been used to run Inkling-2-Mini-UD-IQ3_XXS?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.