Model benchmarks
IsValorum-Ornith-1.5-35B-A3B.APEX-I-MiniPlus-V2.1 local LLM performance
As of October 2026, IsValorum-Ornith-1.5-35B-A3B.APEX-I-MiniPlus-V2.1 runs at up to 15.8 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
15.8 tok/s
Average speed
15.5 tok/s
Avg PP
81.1 tok/s
Min memory
n/a
Max context
200,000 tokens
Avg output / run
36,971 tokens
Avg runtime / run
40m 28s
Avg quality
84.4
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 | 83.1 | 84.4 | 85.7 |
| Agent Workflow | 90.3 | 91.4 | 92.4 |
| Code Generation | 74.2 | 76.1 | 78.0 |
| Role Play & Narrative | 79.2 | 82.5 | 85.8 |
| Research & Analysis | 84.7 | 87.6 | 90.6 |
Performance by hardware and tool
Every hardware/tool/quantization combination IsValorum-Ornith-1.5-35B-A3B.APEX-I-MiniPlus-V2.1 has been benchmarked on, ranked by peak token generation speed. Last updated October 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Intel Graphics | llama.cpp:vulkan | — | 15.8 tok/s | 15.5 tok/s | n/a | 200,000 tokens | 84.4 | 2 |
Benchmark runs
All 2 IsValorum-Ornith-1.5-35B-A3B.APEX-I-MiniPlus-V2.1 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is IsValorum-Ornith-1.5-35B-A3B.APEX-I-MiniPlus-V2.1 good for coding?
- In our benchmarks, IsValorum-Ornith-1.5-35B-A3B.APEX-I-MiniPlus-V2.1 scores 76.1/100 for coding. It runs at about 15.5 tok/s, so if you want more speed, IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF:1 is faster (~25.7 tok/s) and still scores well for coding (85.0/100).
- Is IsValorum-Ornith-1.5-35B-A3B.APEX-I-MiniPlus-V2.1 good for agentic (tool-using) tasks?
- In our benchmarks, IsValorum-Ornith-1.5-35B-A3B.APEX-I-MiniPlus-V2.1 scores 91.4/100 for agentic workflows. It runs at about 15.5 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 IsValorum-Ornith-1.5-35B-A3B.APEX-I-MiniPlus-V2.1 for local inference?
- Across 2 community benchmark runs, IsValorum-Ornith-1.5-35B-A3B.APEX-I-MiniPlus-V2.1 reaches up to 15.8 tok/s and averages 15.5 tok/s, with the fastest results on Intel Graphics.
- Which tools have been used to run IsValorum-Ornith-1.5-35B-A3B.APEX-I-MiniPlus-V2.1?
- Benchmarks were submitted using llama.cpp:vulkan. Results are community-contributed and updated as new runs arrive.