Model benchmarks
ling-tiny local LLM performance
As of September 2026, ling-tiny runs at up to 3774429.8 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
3774429.8 tok/s
Average speed
1887238.2 tok/s
Avg prefill
206.6 tok/s
Min memory
3.4 GB
Max context
8,192 tokens
Avg output / run
14,602 tokens
Avg runtime / run
5m 36s
Avg quality
41.0
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 | 33.3 | 41.0 | 48.8 |
| Agent Workflow | 36.4 | 51.6 | 66.9 |
| Code Generation | 2.8 | 14.1 | 25.4 |
| Role Play & Narrative | 34.6 | 44.0 | 53.3 |
| Research & Analysis | 40.8 | 54.5 | 68.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination ling-tiny 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 |
|---|---|---|---|---|---|---|---|---|
| Apple M1 | LM Studio | — | 3774429.8 tok/s | 1887238.2 tok/s | 3.4 GB | 8,192 tokens | 41.0 | 2 |
Frequently asked questions
- How fast is ling-tiny for local inference?
- Across 2 community benchmark runs, ling-tiny reaches up to 3774429.8 tok/s and averages 1887238.2 tok/s, with the fastest results on Apple M1.
- How much memory does ling-tiny need?
- The leanest observed configuration used about 3.4 GB of memory.
- Which tools have been used to run ling-tiny?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.