Model benchmarks
ling-3.0-flash local LLM performance
As of October 2026, ling-3.0-flash runs at up to 70.5 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
70.5 tok/s
Average speed
68.6 tok/s
Avg PP
163.7 tok/s
Min memory
n/a
Max context
8,192 tokens
Avg output / run
10,208 tokens
Avg runtime / run
2m 52s
Avg quality
61.5
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 | 58.9 | 61.5 | 64.1 |
| Agent Workflow | 80.6 | 85.2 | 89.9 |
| Code Generation | 0.4 | 3.8 | 7.1 |
| Role Play & Narrative | 72.8 | 74.9 | 77.1 |
| Research & Analysis | 82.1 | 82.2 | 82.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination ling-3.0-flash has been benchmarked on, ranked by peak token generation speed. Last updated October 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon AI PRO R9700 | Strata | — | 70.5 tok/s | 68.6 tok/s | n/a | 8,192 tokens | 61.5 | 2 |
Benchmark runs
All 2 ling-3.0-flash runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is ling-3.0-flash good for coding?
- In our benchmarks, ling-3.0-flash scores 3.8/100 for coding. It runs at about 68.6 tok/s, so if you want more speed, ornith-ai/Ornith-1.5-35B-A3B-GGUF is faster (~90.8 tok/s) and still scores well for coding (83.8/100).
- Is ling-3.0-flash good for agentic (tool-using) tasks?
- In our benchmarks, ling-3.0-flash scores 85.2/100 for agentic workflows. It runs at about 68.6 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 ling-3.0-flash for local inference?
- Across 2 community benchmark runs, ling-3.0-flash reaches up to 70.5 tok/s and averages 68.6 tok/s, with the fastest results on AMD Radeon AI PRO R9700.
- Which tools have been used to run ling-3.0-flash?
- Benchmarks were submitted using Strata. Results are community-contributed and updated as new runs arrive.