Model benchmarks
ornith-1.5-35b-a3b-apex-mtp-quality local LLM performance
As of November 2026, ornith-1.5-35b-a3b-apex-mtp-quality runs at up to 103.9 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
103.9 tok/s
Average speed
103.8 tok/s
Avg PP
375.2 tok/s
Min memory
11.9 GB
Max context
65,536 tokens
Avg output / run
43,545 tokens
Avg runtime / run
7m 5s
Avg quality
87.1
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 | 86.4 | 87.1 | 87.9 |
| Agent Workflow | 84.3 | 87.9 | 91.6 |
| Code Generation | 79.4 | 81.2 | 83.0 |
| Role Play & Narrative | 88.4 | 90.9 | 93.3 |
| Research & Analysis | 88.4 | 88.4 | 88.5 |
Performance by hardware and tool
Every hardware/tool/quantization combination ornith-1.5-35b-a3b-apex-mtp-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 4070 | llama.cpp | — | 103.9 tok/s | 103.8 tok/s | 11.9 GB | 65,536 tokens | 87.1 | 2 |
Benchmark runs
All 2 ornith-1.5-35b-a3b-apex-mtp-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-mtp-quality good for agentic (tool-using) tasks?
- In our benchmarks, ornith-1.5-35b-a3b-apex-mtp-quality scores 87.9/100 for agentic workflows. It runs at about 103.8 tok/s, so if you want more speed, gpt-oss-20b-MXFP4 is faster (~119.7 tok/s) and still scores well for agentic workflows (83.3/100).
- How fast is ornith-1.5-35b-a3b-apex-mtp-quality for local inference?
- Across 2 community benchmark runs, ornith-1.5-35b-a3b-apex-mtp-quality reaches up to 103.9 tok/s and averages 103.8 tok/s, with the fastest results on NVIDIA GeForce RTX 4070.
- How much memory does ornith-1.5-35b-a3b-apex-mtp-quality need?
- The leanest observed configuration used about 11.9 GB of memory.
- Which tools have been used to run ornith-1.5-35b-a3b-apex-mtp-quality?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.