Model benchmarks
luciole-1b-instruct-1.1 local LLM performance
As of October 2026, luciole-1b-instruct-1.1 runs at up to 63.1 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
1B
Peak speed
63.1 tok/s
Average speed
61.7 tok/s
Avg PP
2741.5 tok/s
Min memory
2.3 GB
Max context
32,768 tokens
Avg output / run
10,369 tokens
Avg runtime / run
2m 57s
Avg quality
21.6
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 | 20.4 | 21.6 | 23.5 |
| Agent Workflow | 19.4 | 31.3 | 49.3 |
| Code Generation | 0.0 | 0.0 | 0.0 |
| Role Play & Narrative | 27.7 | 37.4 | 43.6 |
| Research & Analysis | 16.9 | 17.6 | 18.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination luciole-1b-instruct-1.1 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 2050 | LM Studio | Q8_0 | 63.1 tok/s | 61.7 tok/s | 2.3 GB | 32,768 tokens | 21.6 | 3 |
Benchmark runs
All 3 luciole-1b-instruct-1.1 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is luciole-1b-instruct-1.1 good for coding?
- In our benchmarks, luciole-1b-instruct-1.1 scores 0.0/100 for coding. It runs at about 61.7 tok/s, so if you want more speed, Ornith-1.5-35B-A3B.APEX-I-NanoPlus is faster (~110.5 tok/s) and still scores well for coding (81.1/100).
- Is luciole-1b-instruct-1.1 good for agentic (tool-using) tasks?
- In our benchmarks, luciole-1b-instruct-1.1 scores 31.3/100 for agentic workflows. It runs at about 61.7 tok/s, so if you want more speed, Nex-N2.5-mini-APEX-Mini is faster (~88.2 tok/s) and still scores well for agentic workflows (91.3/100).
- How fast is luciole-1b-instruct-1.1 for local inference?
- Across 3 community benchmark runs, luciole-1b-instruct-1.1 reaches up to 63.1 tok/s and averages 61.7 tok/s, with the fastest results on NVIDIA GeForce RTX 2050.
- How much memory does luciole-1b-instruct-1.1 need?
- The leanest observed configuration used about 2.3 GB of memory (quantizations tested: Q8_0).
- Which tools have been used to run luciole-1b-instruct-1.1?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.