Model benchmarks
Ornith-1.0-35B-MTPLX local LLM performance
As of August 2026, Ornith-1.0-35B-MTPLX runs at up to 124.0 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
124.0 tok/s
Average speed
104.5 tok/s
Min memory
18.9 GB
Max context
65,536 tokens
Avg runtime / run
2m 7s
Avg quality
80.3
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 | 79.3 | 80.3 | 81.3 |
| Agent Workflow | 79.2 | 81.9 | 84.7 |
| Code Generation | 68.6 | 70.7 | 72.8 |
| Role Play & Narrative | 90.0 | 90.1 | 90.3 |
| Research & Analysis | 77.8 | 78.4 | 79.1 |
Performance by hardware and tool
Every hardware/tool/quantization combination Ornith-1.0-35B-MTPLX has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Max | oMLX | — | 124.0 tok/s | 104.5 tok/s | 18.9 GB | 65,536 tokens | 80.3 | 2 |
Benchmark runs
All 2 Ornith-1.0-35B-MTPLX runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Ornith-1.0-35B-MTPLX good for agentic (tool-using) tasks?
- In our benchmarks, Ornith-1.0-35B-MTPLX scores 81.9/100 for agentic workflows. It runs at about 104.5 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-MLX-oQ4e-MTP is faster (~123.7 tok/s) and still scores well for agentic workflows (84.4/100).
- How fast is Ornith-1.0-35B-MTPLX for local inference?
- Across 2 community benchmark runs, Ornith-1.0-35B-MTPLX reaches up to 124.0 tok/s and averages 104.5 tok/s, with the fastest results on Apple M5 Max.
- How much memory does Ornith-1.0-35B-MTPLX need?
- The leanest observed configuration used about 18.9 GB of memory.
- Which tools have been used to run Ornith-1.0-35B-MTPLX?
- Benchmarks were submitted using oMLX. Results are community-contributed and updated as new runs arrive.