Model benchmarks
cyber-ornith:latest local LLM performance
As of November 2026, cyber-ornith:latest runs at up to 36.3 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
36.3 tok/s
Average speed
35.9 tok/s
Avg PP
1227.0 tok/s
Min memory
n/a
Max context
32,768 tokens
Avg output / run
3,971 tokens
Avg runtime / run
2m 1s
Avg quality
36.9
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 | 29.5 | 36.9 | 44.2 |
| Agent Workflow | 28.6 | 49.7 | 70.8 |
| Code Generation | 0.7 | 6.8 | 12.8 |
| Role Play & Narrative | 57.0 | 57.0 | 57.0 |
| Research & Analysis | 19.5 | 34.1 | 48.6 |
Performance by hardware and tool
Every hardware/tool/quantization combination cyber-ornith:latest 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 3060 | Ollama | Q6_K | 36.3 tok/s | 35.9 tok/s | n/a | 32,768 tokens | 36.9 | 2 |
Benchmark runs
All 2 cyber-ornith:latest runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is cyber-ornith:latest good for coding?
- In our benchmarks, cyber-ornith:latest scores 6.8/100 for coding. It runs at about 35.9 tok/s, so if you want more speed, local-qwen is faster (~60.2 tok/s) and still scores well for coding (84.8/100).
- Is cyber-ornith:latest good for agentic (tool-using) tasks?
- In our benchmarks, cyber-ornith:latest scores 49.7/100 for agentic workflows. It runs at about 35.9 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 cyber-ornith:latest for local inference?
- Across 2 community benchmark runs, cyber-ornith:latest reaches up to 36.3 tok/s and averages 35.9 tok/s, with the fastest results on NVIDIA GeForce RTX 3060.
- Which tools have been used to run cyber-ornith:latest?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.