Model benchmarks
ornith-1.0-9b local LLM performance
As of July 2026, ornith-1.0-9b runs at up to 62.5 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
LM Studio
Model size
9B
Peak speed
62.5 tok/s
Average speed
61.3 tok/s
Min memory
8.9 GB
Max context
16,384 tokens
Avg quality
72.6
Benchmark runs
3
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 3 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 | 71.3 | 72.6 | 73.5 |
| Agent Workflow | 75.0 | 79.9 | 84.0 |
| Code Generation | 51.4 | 57.5 | 62.9 |
| Role Play & Narrative | 79.7 | 82.0 | 85.0 |
| Research & Analysis | 70.2 | 71.1 | 72.6 |
Performance by hardware and tool
Every hardware/tool/quantization combination ornith-1.0-9b has been benchmarked on, ranked by peak token generation speed. Last updated July 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 4070 Ti SUPER | LM Studio | — | 62.5 tok/s | 61.3 tok/s | 8.9 GB | 16,384 tokens | 72.6 | 3 |
Frequently asked questions
- Is ornith-1.0-9b good for coding?
- In our benchmarks, ornith-1.0-9b scores 57.5/100 for coding. It runs at about 61.3 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 ornith-1.0-9b good for agentic (tool-using) tasks?
- In our benchmarks, ornith-1.0-9b scores 79.8/100 for agentic workflows. It runs at about 61.3 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 ornith-1.0-9b for local inference?
- Across 3 community benchmark runs, ornith-1.0-9b reaches up to 62.5 tok/s and averages 61.3 tok/s, with the fastest results on NVIDIA GeForce RTX 4070 Ti SUPER.
- How much memory does ornith-1.0-9b need?
- The leanest observed configuration used about 8.9 GB of memory.
- Which tools have been used to run ornith-1.0-9b?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.