Model benchmarks
Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV local LLM performance
As of November 2026, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV runs at up to 136.3 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
136.3 tok/s
Average speed
132.9 tok/s
Avg PP
3147.6 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg output / run
70,424 tokens
Avg runtime / run
8m 30s
Avg quality
86.6
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 | 85.1 | 86.6 | 87.6 |
| Agent Workflow | 89.6 | 90.7 | 91.7 |
| Code Generation | 68.5 | 73.8 | 78.3 |
| Role Play & Narrative | 90.3 | 92.9 | 95.2 |
| Research & Analysis | 87.6 | 89.0 | 90.0 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV 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 |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon AI PRO R9700 | radiance | — | 136.3 tok/s | 132.9 tok/s | n/a | 65,536 tokens | 86.6 | 3 |
Benchmark runs
All 3 Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV good for coding?
- In our benchmarks, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV scores 73.8/100 for coding. It runs at about 132.9 tok/s, so if you want more speed, swift-1.5-27b-full is faster (~161.4 tok/s) and still scores well for coding (82.7/100).
- Is Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV scores 90.7/100 for agentic workflows. It runs at about 132.9 tok/s, so if you want more speed, swift-1.5-qwen3.8-flash-next-iq3_s is faster (~259.0 tok/s) and still scores well for agentic workflows (88.9/100).
- How fast is Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV for local inference?
- Across 3 community benchmark runs, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV reaches up to 136.3 tok/s and averages 132.9 tok/s, with the fastest results on AMD Radeon AI PRO R9700.
- Which tools have been used to run Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV?
- Benchmarks were submitted using radiance. Results are community-contributed and updated as new runs arrive.