Model benchmarks
Ornith-1.5-35B-A3B-APEX-MTP-I-Quality-MTP-ngram local LLM performance
As of November 2026, Ornith-1.5-35B-A3B-APEX-MTP-I-Quality-MTP-ngram runs at up to 151.1 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
151.1 tok/s
Average speed
150.8 tok/s
Avg PP
2268.8 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg output / run
34,601 tokens
Avg runtime / run
4m 8s
Avg quality
86.1
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 | 85.2 | 86.1 | 87.0 |
| Agent Workflow | 88.8 | 90.1 | 91.4 |
| Code Generation | 80.2 | 82.1 | 84.0 |
| Role Play & Narrative | 80.4 | 83.0 | 85.6 |
| Research & Analysis | 88.6 | 89.1 | 89.5 |
Performance by hardware and tool
Every hardware/tool/quantization combination Ornith-1.5-35B-A3B-APEX-MTP-I-Quality-MTP-ngram 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 |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon AI PRO R9700 | llama.cpp | — | 151.1 tok/s | 150.8 tok/s | n/a | 65,536 tokens | 86.1 | 2 |
Benchmark runs
All 2 Ornith-1.5-35B-A3B-APEX-MTP-I-Quality-MTP-ngram 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-I-Quality-MTP-ngram good for agentic (tool-using) tasks?
- In our benchmarks, Ornith-1.5-35B-A3B-APEX-MTP-I-Quality-MTP-ngram scores 90.1/100 for agentic workflows. It runs at about 150.8 tok/s, so if you want more speed, swift-1.5-qwen3.8-flash-next-iq3_s is faster (~259.0 tok/s) and still scores well for agentic workflows (88.9/100).
- How fast is Ornith-1.5-35B-A3B-APEX-MTP-I-Quality-MTP-ngram for local inference?
- Across 2 community benchmark runs, Ornith-1.5-35B-A3B-APEX-MTP-I-Quality-MTP-ngram reaches up to 151.1 tok/s and averages 150.8 tok/s, with the fastest results on AMD Radeon AI PRO R9700.
- Which tools have been used to run Ornith-1.5-35B-A3B-APEX-MTP-I-Quality-MTP-ngram?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.