Model benchmarks
Qwen3.8-27B-GSQ-RCO-IQ3_XXS local LLM performance
As of October 2026, Qwen3.8-27B-GSQ-RCO-IQ3_XXS runs at up to 41.9 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
41.9 tok/s
Average speed
40.6 tok/s
Avg PP
499.7 tok/s
Min memory
19.6 GB
Max context
131,072 tokens
Avg output / run
15,824 tokens
Avg runtime / run
6m 22s
Avg quality
84.1
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 | 83.0 | 84.1 | 85.2 |
| Agent Workflow | 77.1 | 78.7 | 80.2 |
| Code Generation | 79.8 | 81.0 | 82.1 |
| Role Play & Narrative | 84.9 | 89.6 | 94.3 |
| Research & Analysis | 86.9 | 87.1 | 87.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.8-27B-GSQ-RCO-IQ3_XXS 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 5060 | llama.cpp | — | 41.9 tok/s | 40.6 tok/s | 19.6 GB | 131,072 tokens | 84.1 | 2 |
Benchmark runs
All 2 Qwen3.8-27B-GSQ-RCO-IQ3_XXS runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Qwen3.8-27B-GSQ-RCO-IQ3_XXS good for coding?
- In our benchmarks, Qwen3.8-27B-GSQ-RCO-IQ3_XXS scores 81.0/100 for coding. It runs at about 40.6 tok/s, so if you want more speed, nvidia/Qwen3.8-27B-NVFP4 is faster (~63.3 tok/s) and still scores well for coding (82.7/100).
- Is Qwen3.8-27B-GSQ-RCO-IQ3_XXS good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.8-27B-GSQ-RCO-IQ3_XXS scores 78.7/100 for agentic workflows. It runs at about 40.6 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 Qwen3.8-27B-GSQ-RCO-IQ3_XXS for local inference?
- Across 2 community benchmark runs, Qwen3.8-27B-GSQ-RCO-IQ3_XXS reaches up to 41.9 tok/s and averages 40.6 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does Qwen3.8-27B-GSQ-RCO-IQ3_XXS need?
- The leanest observed configuration used about 19.6 GB of memory.
- Which tools have been used to run Qwen3.8-27B-GSQ-RCO-IQ3_XXS?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.