Model benchmarks
Qwen3.8-MXFP4 local LLM performance
As of October 2026, Qwen3.8-MXFP4 runs at up to 67.6 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
67.6 tok/s
Average speed
66.4 tok/s
Avg PP
2269.3 tok/s
Min memory
n/a
Max context
155,648 tokens
Avg output / run
12,564 tokens
Avg runtime / run
3m 5s
Avg quality
83.9
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 | 83.9 | 85.1 |
| Agent Workflow | 79.2 | 85.6 | 89.6 |
| Code Generation | 69.8 | 74.9 | 78.8 |
| Role Play & Narrative | 84.9 | 89.1 | 92.0 |
| Research & Analysis | 81.2 | 86.0 | 89.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.8-MXFP4 has been benchmarked on, ranked by peak token generation speed. Last updated October 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon AI PRO R9700 | vLLM | — | 67.6 tok/s | 66.4 tok/s | n/a | 155,648 tokens | 83.9 | 3 |
Benchmark runs
All 3 Qwen3.8-MXFP4 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Qwen3.8-MXFP4 good for coding?
- In our benchmarks, Qwen3.8-MXFP4 scores 74.9/100 for coding. It runs at about 66.4 tok/s, so if you want more speed, ornith-ai/Ornith-1.5-35B-A3B-GGUF is faster (~90.8 tok/s) and still scores well for coding (83.8/100).
- Is Qwen3.8-MXFP4 good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.8-MXFP4 scores 85.6/100 for agentic workflows. It runs at about 66.4 tok/s, so if you want more speed, Nex-N2.5-mini-APEX-Mini is faster (~88.2 tok/s) and still scores well for agentic workflows (91.3/100).
- How fast is Qwen3.8-MXFP4 for local inference?
- Across 3 community benchmark runs, Qwen3.8-MXFP4 reaches up to 67.6 tok/s and averages 66.4 tok/s, with the fastest results on AMD Radeon AI PRO R9700.
- Which tools have been used to run Qwen3.8-MXFP4?
- Benchmarks were submitted using vLLM. Results are community-contributed and updated as new runs arrive.