Model benchmarks
ornith-1.5-35b-a3b-apex-i-quality local LLM performance
As of November 2026, ornith-1.5-35b-a3b-apex-i-quality runs at up to 93.2 tok/s for local inference (best of 3 community benchmark runs across 2 GPUs).
Model size
35B
Peak speed
93.2 tok/s
Average speed
59.4 tok/s
Avg PP
331.3 tok/s
Min memory
10.3 GB
Max context
131,072 tokens
Avg output / run
36,201 tokens
Avg runtime / run
11m 59s
Avg quality
86.8
Benchmark runs
3
GPUs tested
2
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 | 86.0 | 86.8 | 87.9 |
| Agent Workflow | 85.5 | 88.4 | 92.2 |
| Code Generation | 78.9 | 82.8 | 85.5 |
| Role Play & Narrative | 85.4 | 89.2 | 92.2 |
| Research & Analysis | 82.1 | 86.8 | 89.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination ornith-1.5-35b-a3b-apex-i-quality has been benchmarked on, ranked by peak token generation speed. Last updated November 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 5060 | PolyStrata | — | 93.2 tok/s | 93.2 tok/s | n/a | 131,072 tokens | 85.9 | 1 |
| NVIDIA GeForce RTX 3070 Ti | Polystrata | — | 42.7 tok/s | 42.4 tok/s | 10.3 GB | 131,072 tokens | 87.2 | 2 |
Benchmark runs
All 3 ornith-1.5-35b-a3b-apex-i-quality runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is ornith-1.5-35b-a3b-apex-i-quality good for coding?
- In our benchmarks, ornith-1.5-35b-a3b-apex-i-quality scores 82.8/100 for coding. It runs at about 59.4 tok/s, so if you want more speed, ornith-ai/Ornith-1.5-35B-A3B-GGUF is faster (~80.3 tok/s) and still scores well for coding (82.1/100).
- Is ornith-1.5-35b-a3b-apex-i-quality good for agentic (tool-using) tasks?
- In our benchmarks, ornith-1.5-35b-a3b-apex-i-quality scores 88.4/100 for agentic workflows. It runs at about 59.4 tok/s, so if you want more speed, swift-iq2_xs is faster (~91.5 tok/s) and still scores well for agentic workflows (91.4/100).
- How fast is ornith-1.5-35b-a3b-apex-i-quality for local inference?
- Across 3 community benchmark runs, ornith-1.5-35b-a3b-apex-i-quality reaches up to 93.2 tok/s and averages 59.4 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does ornith-1.5-35b-a3b-apex-i-quality need?
- The leanest observed configuration used about 10.3 GB of memory.
- Which tools have been used to run ornith-1.5-35b-a3b-apex-i-quality?
- Benchmarks were submitted using PolyStrata, Polystrata. Results are community-contributed and updated as new runs arrive.