Model benchmarks
Ornith-1.5-35B-A3B-oQ6e-mtp local LLM performance
As of September 2026, Ornith-1.5-35B-A3B-oQ6e-mtp runs at up to 62.6 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
62.6 tok/s
Average speed
59.2 tok/s
Avg PP
582.7 tok/s
Min memory
29.3 GB
Max context
262,144 tokens
Avg output / run
38,200 tokens
Avg runtime / run
11m 22s
Avg quality
83.4
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 | 81.4 | 83.4 | 85.4 |
| Agent Workflow | 84.1 | 88.2 | 90.9 |
| Code Generation | 74.1 | 76.5 | 78.6 |
| Role Play & Narrative | 84.6 | 86.4 | 89.3 |
| Research & Analysis | 82.4 | 82.7 | 82.8 |
Performance by hardware and tool
Every hardware/tool/quantization combination Ornith-1.5-35B-A3B-oQ6e-mtp has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Apple M4 Pro | oMLX | — | 62.6 tok/s | 59.2 tok/s | 29.3 GB | 262,144 tokens | 83.4 | 3 |
Benchmark runs
All 3 Ornith-1.5-35B-A3B-oQ6e-mtp runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Ornith-1.5-35B-A3B-oQ6e-mtp good for coding?
- In our benchmarks, Ornith-1.5-35B-A3B-oQ6e-mtp scores 76.5/100 for coding. It runs at about 59.2 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-A3B-oQ6e-mtp good for agentic (tool-using) tasks?
- In our benchmarks, Ornith-1.5-35B-A3B-oQ6e-mtp scores 88.2/100 for agentic workflows. It runs at about 59.2 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-A3B-oQ6e-mtp for local inference?
- Across 3 community benchmark runs, Ornith-1.5-35B-A3B-oQ6e-mtp reaches up to 62.6 tok/s and averages 59.2 tok/s, with the fastest results on Apple M4 Pro.
- How much memory does Ornith-1.5-35B-A3B-oQ6e-mtp need?
- The leanest observed configuration used about 29.3 GB of memory.
- Which tools have been used to run Ornith-1.5-35B-A3B-oQ6e-mtp?
- Benchmarks were submitted using oMLX. Results are community-contributed and updated as new runs arrive.