Model benchmarks
Ornith-1.5-9B-oQ8e local LLM performance
As of August 2026, Ornith-1.5-9B-oQ8e runs at up to 53.1 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
oMLX
Model size
9B
Peak speed
53.1 tok/s
Average speed
53.0 tok/s
Min memory
11.5 GB
Max context
58,469 tokens
Best quality
89.8
Benchmark runs
2
GPUs tested
1
Performance by hardware and tool
Every hardware/tool/quantization combination Ornith-1.5-9B-oQ8e has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Max | oMLX | — | 53.1 tok/s | 53.0 tok/s | 11.5 GB | 58,469 tokens | 65.6 | 2 |
Frequently asked questions
- How fast is Ornith-1.5-9B-oQ8e for local inference?
- Across 2 community benchmark runs, Ornith-1.5-9B-oQ8e reaches up to 53.1 tok/s and averages 53.0 tok/s, with the fastest results on Apple M5 Max.
- How much memory does Ornith-1.5-9B-oQ8e need?
- The leanest observed configuration used about 11.5 GB of memory.
- Which tools have been used to run Ornith-1.5-9B-oQ8e?
- Benchmarks were submitted using oMLX. Results are community-contributed and updated as new runs arrive.