Model benchmarks
Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-bf16KV local LLM performance
As of November 2026, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-bf16KV runs at up to 135.5 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
135.5 tok/s
Average speed
129.2 tok/s
Avg PP
3151.1 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg output / run
78,861 tokens
Avg runtime / run
9m 45s
Avg quality
86.6
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 | 85.7 | 86.6 | 87.6 |
| Agent Workflow | 89.3 | 91.5 | 93.7 |
| Code Generation | 68.1 | 74.5 | 80.9 |
| Role Play & Narrative | 90.8 | 93.2 | 95.5 |
| Research & Analysis | 85.3 | 87.4 | 89.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-bf16KV 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 | — | 135.5 tok/s | 129.2 tok/s | n/a | 65,536 tokens | 86.6 | 2 |
Benchmark runs
All 2 Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-bf16KV 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-bf16KV good for coding?
- In our benchmarks, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-bf16KV scores 74.5/100 for coding. It runs at about 129.2 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-bf16KV good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-bf16KV scores 91.5/100 for agentic workflows. It runs at about 129.2 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-bf16KV for local inference?
- Across 2 community benchmark runs, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-bf16KV reaches up to 135.5 tok/s and averages 129.2 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-bf16KV?
- Benchmarks were submitted using radiance. Results are community-contributed and updated as new runs arrive.