Model benchmarks
Qwen3.8-27B-IQ3_XXS local LLM performance
As of August 2026, Qwen3.8-27B-IQ3_XXS runs at up to 61.1 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
61.1 tok/s
Average speed
59.6 tok/s
Min memory
13.2 GB
Max context
65,536 tokens
Avg output / run
16,510 tokens
Avg runtime / run
4m 35s
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 | 83.3 | 84.4 | 85.4 |
| Agent Workflow | 81.3 | 84.0 | 86.7 |
| Code Generation | 70.2 | 75.9 | 81.6 |
| Role Play & Narrative | 92.0 | 93.5 | 95.0 |
| Research & Analysis | 83.9 | 84.0 | 84.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.8-27B-IQ3_XXS has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M | llama.cpp | — | 61.1 tok/s | 59.6 tok/s | 13.2 GB | 65,536 tokens | 84.4 | 2 |
Frequently asked questions
- Is Qwen3.8-27B-IQ3_XXS good for coding?
- In our benchmarks, Qwen3.8-27B-IQ3_XXS scores 75.9/100 for coding. It runs at about 59.6 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-MLX-oQ4e-MTP is faster (~123.6 tok/s) and still scores well for coding (76.5/100).
- Is Qwen3.8-27B-IQ3_XXS good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.8-27B-IQ3_XXS scores 84.0/100 for agentic workflows. It runs at about 59.6 tok/s, so if you want more speed, openai/gpt-oss-20b:2 is faster (~154.8 tok/s) and still scores well for agentic workflows (87.2/100).
- How fast is Qwen3.8-27B-IQ3_XXS for local inference?
- Across 2 community benchmark runs, Qwen3.8-27B-IQ3_XXS reaches up to 61.1 tok/s and averages 59.6 tok/s, with the fastest results on AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M.
- How much memory does Qwen3.8-27B-IQ3_XXS need?
- The leanest observed configuration used about 13.2 GB of memory.
- Which tools have been used to run Qwen3.8-27B-IQ3_XXS?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.