Model benchmarks
Qwen3.8-27B-MTPLX-Optimized-Speed local LLM performance
As of September 2026, Qwen3.8-27B-MTPLX-Optimized-Speed runs at up to 52.7 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
52.7 tok/s
Average speed
51.5 tok/s
Avg PP
608.5 tok/s
Min memory
26.2 GB
Max context
131.072 tokens
Avg output / run
20.578 tokens
Avg runtime / run
6m 39s
Avg quality
84.2
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 | 81.9 | 84.2 | 86.5 |
| Agent Workflow | 82.7 | 85.2 | 87.8 |
| Code Generation | 74.7 | 77.6 | 80.5 |
| Role Play & Narrative | 85.6 | 89.9 | 94.3 |
| Research & Analysis | 83.4 | 83.9 | 84.5 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.8-27B-MTPLX-Optimized-Speed 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 |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Max | oMLX | — | 52.7 tok/s | 51.5 tok/s | 26.2 GB | 131.072 tokens | 84.2 | 2 |
Benchmark runs
All 2 Qwen3.8-27B-MTPLX-Optimized-Speed runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Qwen3.8-27B-MTPLX-Optimized-Speed good for coding?
- In our benchmarks, Qwen3.8-27B-MTPLX-Optimized-Speed scores 77.6/100 for coding. It runs at about 51.5 tok/s, so if you want more speed, local-qwen is faster (~60.2 tok/s) and still scores well for coding (84.8/100).
- Is Qwen3.8-27B-MTPLX-Optimized-Speed good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.8-27B-MTPLX-Optimized-Speed scores 85.2/100 for agentic workflows. It runs at about 51.5 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 Qwen3.8-27B-MTPLX-Optimized-Speed for local inference?
- Across 2 community benchmark runs, Qwen3.8-27B-MTPLX-Optimized-Speed reaches up to 52.7 tok/s and averages 51.5 tok/s, with the fastest results on Apple M5 Max.
- How much memory does Qwen3.8-27B-MTPLX-Optimized-Speed need?
- The leanest observed configuration used about 26.2 GB of memory.
- Which tools have been used to run Qwen3.8-27B-MTPLX-Optimized-Speed?
- Benchmarks were submitted using oMLX. Results are community-contributed and updated as new runs arrive.