Model benchmarks
Groot-19B-A3B-261023.APEX-I-MiniPlus-V2.1 local LLM performance
As of November 2026, Groot-19B-A3B-261023.APEX-I-MiniPlus-V2.1 runs at up to 20.5 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
19B
Peak speed
20.5 tok/s
Average speed
19.5 tok/s
Avg PP
119.6 tok/s
Min memory
n/a
Max context
200,000 tokens
Avg output / run
27,661 tokens
Avg runtime / run
24m 54s
Avg quality
73.6
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 | 70.6 | 73.6 | 76.2 |
| Agent Workflow | 64.5 | 73.6 | 81.1 |
| Code Generation | 69.2 | 70.9 | 72.6 |
| Role Play & Narrative | 68.7 | 69.5 | 70.6 |
| Research & Analysis | 77.4 | 80.1 | 84.0 |
Performance by hardware and tool
Every hardware/tool/quantization combination Groot-19B-A3B-261023.APEX-I-MiniPlus-V2.1 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 |
|---|---|---|---|---|---|---|---|---|
| Intel Graphics | llama.cpp | — | 20.5 tok/s | 20.4 tok/s | n/a | 200,000 tokens | 75.2 | 2 |
| Intel Graphics | llama.cpp:vulkan | — | 17.7 tok/s | 17.7 tok/s | n/a | 200,000 tokens | 70.2 | 1 |
Benchmark runs
All 3 Groot-19B-A3B-261023.APEX-I-MiniPlus-V2.1 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Groot-19B-A3B-261023.APEX-I-MiniPlus-V2.1 good for coding?
- In our benchmarks, Groot-19B-A3B-261023.APEX-I-MiniPlus-V2.1 scores 70.9/100 for coding. It runs at about 19.5 tok/s, so if you want more speed, IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF:1 is faster (~25.2 tok/s) and still scores well for coding (84.9/100).
- Is Groot-19B-A3B-261023.APEX-I-MiniPlus-V2.1 good for agentic (tool-using) tasks?
- In our benchmarks, Groot-19B-A3B-261023.APEX-I-MiniPlus-V2.1 scores 73.6/100 for agentic workflows. It runs at about 19.5 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 Groot-19B-A3B-261023.APEX-I-MiniPlus-V2.1 for local inference?
- Across 3 community benchmark runs, Groot-19B-A3B-261023.APEX-I-MiniPlus-V2.1 reaches up to 20.5 tok/s and averages 19.5 tok/s, with the fastest results on Intel Graphics.
- Which tools have been used to run Groot-19B-A3B-261023.APEX-I-MiniPlus-V2.1?
- Benchmarks were submitted using llama.cpp, llama.cpp:vulkan. Results are community-contributed and updated as new runs arrive.