Model benchmarks
qwen3.5-9b-mtp@q8_0 local LLM performance
As of September 2026, qwen3.5-9b-mtp@q8_0 runs at up to 45.0 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
9B
Peak speed
45.0 tok/s
Average speed
41.8 tok/s
Avg PP
857.0 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg output / run
19,745 tokens
Avg runtime / run
8m 22s
Avg quality
67.5
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 | 66.8 | 67.5 | 68.3 |
| Agent Workflow | 60.4 | 62.6 | 64.0 |
| Code Generation | 51.4 | 56.2 | 63.0 |
| Role Play & Narrative | 72.1 | 80.5 | 85.8 |
| Research & Analysis | 68.6 | 70.7 | 72.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen3.5-9b-mtp@q8_0 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 7600 XT | LM Studio | Q8_0 | 45.0 tok/s | 41.8 tok/s | n/a | 65,536 tokens | 67.5 | 3 |
Benchmark runs
All 3 qwen3.5-9b-mtp@q8_0 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is qwen3.5-9b-mtp@q8_0 good for coding?
- In our benchmarks, qwen3.5-9b-mtp@q8_0 scores 56.2/100 for coding. It runs at about 41.8 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 qwen3.5-9b-mtp@q8_0 good for agentic (tool-using) tasks?
- In our benchmarks, qwen3.5-9b-mtp@q8_0 scores 62.6/100 for agentic workflows. It runs at about 41.8 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 qwen3.5-9b-mtp@q8_0 for local inference?
- Across 3 community benchmark runs, qwen3.5-9b-mtp@q8_0 reaches up to 45.0 tok/s and averages 41.8 tok/s, with the fastest results on AMD Radeon RX 7600 XT.
- Which tools have been used to run qwen3.5-9b-mtp@q8_0?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.