Model benchmarks
occamy-1.0.i1-IQ3_XXS local LLM performance
As of September 2026, occamy-1.0.i1-IQ3_XXS runs at up to 80.2 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
80.2 tok/s
Average speed
78.2 tok/s
Avg PP
845.1 tok/s
Min memory
16.2 GB
Max context
131,072 tokens
Avg output / run
79,323 tokens
Avg runtime / run
18m 31s
Avg quality
66.6
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 | 50.9 | 66.6 | 83.2 |
| Agent Workflow | 20.8 | 64.1 | 90.4 |
| Code Generation | 3.9 | 28.7 | 68.6 |
| Role Play & Narrative | 87.4 | 89.4 | 90.7 |
| Research & Analysis | 83.0 | 84.4 | 86.1 |
Performance by hardware and tool
Every hardware/tool/quantization combination occamy-1.0.i1-IQ3_XXS has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 5060 | llama.cpp | — | 80.2 tok/s | 78.2 tok/s | 16.2 GB | 131,072 tokens | 66.6 | 3 |
Benchmark runs
All 3 occamy-1.0.i1-IQ3_XXS runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is occamy-1.0.i1-IQ3_XXS good for coding?
- In our benchmarks, occamy-1.0.i1-IQ3_XXS scores 28.7/100 for coding. It runs at about 78.2 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-MLX-oQ4e is faster (~97.4 tok/s) and still scores well for coding (80.9/100).
- Is occamy-1.0.i1-IQ3_XXS good for agentic (tool-using) tasks?
- In our benchmarks, occamy-1.0.i1-IQ3_XXS scores 64.1/100 for agentic workflows. It runs at about 78.2 tok/s, so if you want more speed, qwen3.8-flash-next-iq3_s is faster (~100.4 tok/s) and still scores well for agentic workflows (90.1/100).
- How fast is occamy-1.0.i1-IQ3_XXS for local inference?
- Across 3 community benchmark runs, occamy-1.0.i1-IQ3_XXS reaches up to 80.2 tok/s and averages 78.2 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does occamy-1.0.i1-IQ3_XXS need?
- The leanest observed configuration used about 16.2 GB of memory.
- Which tools have been used to run occamy-1.0.i1-IQ3_XXS?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.