Model benchmarks
ling-oq8e local LLM performance
As of September 2026, ling-oq8e runs at up to 33.9 tok/s for local inference (best of 6 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
33.9 tok/s
Average speed
33.8 tok/s
Avg prefill
407.0 tok/s
Min memory
6.8 GB
Max context
8,192 tokens
Avg output / run
19,962 tokens
Avg runtime / run
10m 7s
Avg quality
44.0
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 | 38.4 | 44.0 | 49.5 |
| Agent Workflow | 40.9 | 73.7 | 90.8 |
| Code Generation | 0.0 | 6.1 | 21.1 |
| Role Play & Narrative | 21.9 | 45.3 | 64.8 |
| Research & Analysis | 20.7 | 51.1 | 70.1 |
Performance by hardware and tool
Every hardware/tool/quantization combination ling-oq8e 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 | — | 33.9 tok/s | 33.8 tok/s | 6.8 GB | 8,192 tokens | 44.0 | 6 |
Frequently asked questions
- Is ling-oq8e good for coding?
- In our benchmarks, ling-oq8e scores 6.1/100 for coding. It runs at about 33.8 tok/s, so if you want more speed, unsloth/Qwen3.8-27B-GGUF:IQ3_S is faster (~104.3 tok/s) and still scores well for coding (83.0/100).
- Is ling-oq8e good for agentic (tool-using) tasks?
- In our benchmarks, ling-oq8e scores 73.7/100 for agentic workflows. It runs at about 33.8 tok/s, so if you want more speed, granite-4.2-8b-Q4_K_L is faster (~71.6 tok/s) and still scores well for agentic workflows (92.9/100).
- How fast is ling-oq8e for local inference?
- Across 6 community benchmark runs, ling-oq8e reaches up to 33.9 tok/s and averages 33.8 tok/s, with the fastest results on Apple M1.
- How much memory does ling-oq8e need?
- The leanest observed configuration used about 6.8 GB of memory.
- Which tools have been used to run ling-oq8e?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.