Model benchmarks
ornith-1.5-9b local LLM performance
As of August 2026, ornith-1.5-9b runs at up to 94.0 tok/s for local inference (best of 4 community benchmark runs across 2 GPUs).
LM Studio
Model size
9B
Peak speed
94.0 tok/s
Average speed
77.3 tok/s
Min memory
4.4 GB
Max context
10,070 tokens
Best quality
90.5
Benchmark runs
4
GPUs tested
2
Performance by hardware and tool
Every hardware/tool/quantization combination ornith-1.5-9b 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 3080 | LM Studio | — | 94.0 tok/s | 93.8 tok/s | 4.4 GB | 6,859 tokens | 54.3 | 3 |
| AMD Radeon RX 7600 XT | LM Studio | — | 27.6 tok/s | 27.6 tok/s | 9.7 GB | 10,070 tokens | 82.6 | 1 |
Frequently asked questions
- How fast is ornith-1.5-9b for local inference?
- Across 4 community benchmark runs, ornith-1.5-9b reaches up to 94.0 tok/s and averages 77.3 tok/s, with the fastest results on NVIDIA GeForce RTX 3080.
- How much memory does ornith-1.5-9b need?
- The leanest observed configuration used about 4.4 GB of memory.
- Which tools have been used to run ornith-1.5-9b?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.