Model benchmarks
Ornith-1.5-35B-Q4_K_M local LLM performance
As of October 2026, Ornith-1.5-35B-Q4_K_M runs at up to 56.5 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
56.5 tok/s
Average speed
54.8 tok/s
Avg PP
346.8 tok/s
Min memory
26.7 GB
Max context
131,072 tokens
Avg output / run
35,211 tokens
Avg runtime / run
11m
Avg quality
87.7
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 | 86.8 | 87.7 | 88.6 |
| Agent Workflow | 89.1 | 89.7 | 90.3 |
| Code Generation | 81.6 | 81.9 | 82.2 |
| Role Play & Narrative | 90.4 | 91.4 | 92.4 |
| Research & Analysis | 84.5 | 87.9 | 91.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination Ornith-1.5-35B-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 5060 | llama.cpp | Q4_K_M | 56.5 tok/s | 54.8 tok/s | 26.7 GB | 131,072 tokens | 87.7 | 2 |
Benchmark runs
All 2 Ornith-1.5-35B-Q4_K_M runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Ornith-1.5-35B-Q4_K_M good for coding?
- In our benchmarks, Ornith-1.5-35B-Q4_K_M scores 81.9/100 for coding. It runs at about 54.8 tok/s, so if you want more speed, ornith-ai/Ornith-1.5-35B-A3B-GGUF is faster (~90.8 tok/s) and still scores well for coding (83.8/100).
- Is Ornith-1.5-35B-Q4_K_M good for agentic (tool-using) tasks?
- In our benchmarks, Ornith-1.5-35B-Q4_K_M scores 89.7/100 for agentic workflows. It runs at about 54.8 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-1.5-35B-Q4_K_M for local inference?
- Across 2 community benchmark runs, Ornith-1.5-35B-Q4_K_M reaches up to 56.5 tok/s and averages 54.8 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does Ornith-1.5-35B-Q4_K_M need?
- The leanest observed configuration used about 26.7 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run Ornith-1.5-35B-Q4_K_M?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.