Model benchmarks
dirk-qwen3.8-27b@iq3_xxs local LLM performance
As of September 2026, dirk-qwen3.8-27b@iq3_xxs runs at up to 19.3 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
19.3 tok/s
Average speed
18.8 tok/s
Avg PP
599.3 tok/s
Min memory
n/a
Max context
120,000 tokens
Avg output / run
12,458 tokens
Avg runtime / run
11m 15s
Avg quality
83.2
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 | 82.4 | 83.2 | 84.4 |
| Agent Workflow | 83.6 | 87.1 | 91.3 |
| Code Generation | 71.3 | 74.5 | 76.9 |
| Role Play & Narrative | 78.1 | 84.9 | 89.8 |
| Research & Analysis | 85.2 | 86.3 | 87.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination dirk-qwen3.8-27b@iq3_xxs has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 9070/9070 XT/9070 GRE | LM Studio | — | 19.3 tok/s | 18.8 tok/s | n/a | 120,000 tokens | 83.2 | 3 |
Benchmark runs
All 3 dirk-qwen3.8-27b@iq3_xxs runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is dirk-qwen3.8-27b@iq3_xxs good for coding?
- In our benchmarks, dirk-qwen3.8-27b@iq3_xxs scores 74.5/100 for coding. It runs at about 18.8 tok/s, so if you want more speed, IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF:1 is faster (~25.2 tok/s) and still scores well for coding (84.9/100).
- Is dirk-qwen3.8-27b@iq3_xxs good for agentic (tool-using) tasks?
- In our benchmarks, dirk-qwen3.8-27b@iq3_xxs scores 87.1/100 for agentic workflows. It runs at about 18.8 tok/s, so if you want more speed, granite-4.2-8b-Q4_K_L is faster (~71.6 tok/s) and still scores well for agentic workflows (92.9/100).
- How fast is dirk-qwen3.8-27b@iq3_xxs for local inference?
- Across 3 community benchmark runs, dirk-qwen3.8-27b@iq3_xxs reaches up to 19.3 tok/s and averages 18.8 tok/s, with the fastest results on AMD Radeon RX 9070/9070 XT/9070 GRE.
- Which tools have been used to run dirk-qwen3.8-27b@iq3_xxs?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.