Model benchmarks
Qwen3.8-Flash-Next-oQ4e-mtp local LLM performance
As of September 2026, Qwen3.8-Flash-Next-oQ4e-mtp runs at up to 25.9 tok/s for local inference (best of 4 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
25.9 tok/s
Average speed
24.7 tok/s
Min memory
68.9 GB
Max context
131,072 tokens
Avg output / run
58,471 tokens
Avg runtime / run
38m 35s
Avg quality
78.4
Benchmark runs
4
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 4 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 | 75.7 | 78.4 | 81.3 |
| Agent Workflow | 77.6 | 85.9 | 91.0 |
| Code Generation | 34.3 | 51.4 | 74.1 |
| Role Play & Narrative | 85.7 | 90.7 | 94.9 |
| Research & Analysis | 80.0 | 85.6 | 88.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.8-Flash-Next-oQ4e-mtp 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 M2 Ultra | oMLX | — | 25.9 tok/s | 24.7 tok/s | 68.9 GB | 131,072 tokens | 78.4 | 4 |
Frequently asked questions
- Is Qwen3.8-Flash-Next-oQ4e-mtp good for coding?
- In our benchmarks, Qwen3.8-Flash-Next-oQ4e-mtp scores 51.4/100 for coding. It runs at about 24.7 tok/s, so if you want more speed, Gemma4:E2B/QAT-MTP@131K is faster (~303.9 tok/s) and still scores well for coding (66.9/100).
- Is Qwen3.8-Flash-Next-oQ4e-mtp good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.8-Flash-Next-oQ4e-mtp scores 85.9/100 for agentic workflows. It runs at about 24.7 tok/s, so if you want more speed, mudler/Ornith-1.5-35B-A3B-APEX-MTP-GGUF is faster (~190.9 tok/s) and still scores well for agentic workflows (85.7/100).
- How fast is Qwen3.8-Flash-Next-oQ4e-mtp for local inference?
- Across 4 community benchmark runs, Qwen3.8-Flash-Next-oQ4e-mtp reaches up to 25.9 tok/s and averages 24.7 tok/s, with the fastest results on Apple M2 Ultra.
- How much memory does Qwen3.8-Flash-Next-oQ4e-mtp need?
- The leanest observed configuration used about 68.9 GB of memory.
- Which tools have been used to run Qwen3.8-Flash-Next-oQ4e-mtp?
- Benchmarks were submitted using oMLX. Results are community-contributed and updated as new runs arrive.