Model benchmarks
Qwen3.8-27B-IQ5R-V4-DFlash2-TP2 local LLM performance
As of November 2026, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2 runs at up to 137.9 tok/s for local inference (best of 11 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
137.9 tok/s
Average speed
128.8 tok/s
Avg PP
3309.6 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg output / run
78,081 tokens
Avg runtime / run
9m 48s
Avg quality
88.1
Benchmark runs
11
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 11 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 | 85.2 | 88.1 | 91.1 |
| Agent Workflow | 86.5 | 90.4 | 92.6 |
| Code Generation | 72.3 | 80.0 | 88.7 |
| Role Play & Narrative | 91.4 | 94.2 | 96.3 |
| Research & Analysis | 85.0 | 87.7 | 90.0 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.8-27B-IQ5R-V4-DFlash2-TP2 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 | — | 137.9 tok/s | 128.8 tok/s | n/a | 65,536 tokens | 88.1 | 11 |
Benchmark runs
All 11 Qwen3.8-27B-IQ5R-V4-DFlash2-TP2 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 good for coding?
- In our benchmarks, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2 scores 80.0/100 for coding. It runs at about 128.8 tok/s, so if you want more speed, ornith-1.5-35b-apex is faster (~149.2 tok/s) and still scores well for coding (83.5/100).
- Is Qwen3.8-27B-IQ5R-V4-DFlash2-TP2 good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2 scores 90.4/100 for agentic workflows. It runs at about 128.8 tok/s, so if you want more speed, Ornith-1.5-35B-A3B-APEX-MTP-I-Quality-MTP-ngram is faster (~150.8 tok/s) and still scores well for agentic workflows (90.1/100).
- How fast is Qwen3.8-27B-IQ5R-V4-DFlash2-TP2 for local inference?
- Across 11 community benchmark runs, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2 reaches up to 137.9 tok/s and averages 128.8 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?
- Benchmarks were submitted using radiance. Results are community-contributed and updated as new runs arrive.