Model benchmarks
ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M local LLM performance
As of October 2026, ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M runs at up to 75.7 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
9B
Peak speed
75.7 tok/s
Average speed
75.2 tok/s
Avg PP
981.2 tok/s
Min memory
9.8 GB
Max context
131,072 tokens
Avg output / run
79,496 tokens
Avg runtime / run
18m 59s
Avg quality
68.7
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 | 63.1 | 68.7 | 77.5 |
| Agent Workflow | 14.1 | 39.7 | 76.1 |
| Code Generation | 65.1 | 68.7 | 72.1 |
| Role Play & Narrative | 82.7 | 86.5 | 89.2 |
| Research & Analysis | 77.4 | 80.1 | 82.8 |
Performance by hardware and tool
Every hardware/tool/quantization combination ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 4070 | llama.cpp | Q4_K_M | 75.7 tok/s | 75.2 tok/s | 9.8 GB | 131,072 tokens | 68.7 | 3 |
Benchmark runs
All 3 ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M good for coding?
- In our benchmarks, ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M scores 68.7/100 for coding. It runs at about 75.2 tok/s, so if you want more speed, Nex-N2.5-mini-IQ3_XXS is faster (~91.4 tok/s) and still scores well for coding (81.6/100).
- Is ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M good for agentic (tool-using) tasks?
- In our benchmarks, ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M scores 39.7/100 for agentic workflows. It runs at about 75.2 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 ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M for local inference?
- Across 3 community benchmark runs, ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M reaches up to 75.7 tok/s and averages 75.2 tok/s, with the fastest results on NVIDIA GeForce RTX 4070.
- How much memory does ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M need?
- The leanest observed configuration used about 9.8 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.