Model benchmarks
qwen35-9b local LLM performance
As of November 2026, qwen35-9b runs at up to 77.5 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
9B
Peak speed
77.5 tok/s
Average speed
75.6 tok/s
Avg PP
1973.4 tok/s
Min memory
10.5 GB
Max context
32,768 tokens
Avg output / run
6,835 tokens
Avg runtime / run
2m 50s
Avg quality
63.9
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 | 54.2 | 63.9 | 73.6 |
| Agent Workflow | 6.7 | 42.6 | 78.5 |
| Code Generation | 56.8 | 60.6 | 64.4 |
| Role Play & Narrative | 78.6 | 82.6 | 86.5 |
| Research & Analysis | 66.9 | 69.8 | 72.6 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen35-9b has been benchmarked on, ranked by peak token generation speed. Last updated November 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 3080 Ti | OpenAI-compatible | — | 77.5 tok/s | 75.6 tok/s | 10.5 GB | 32,768 tokens | 63.9 | 2 |
Benchmark runs
All 2 qwen35-9b runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is qwen35-9b good for coding?
- In our benchmarks, qwen35-9b scores 60.6/100 for coding. It runs at about 75.6 tok/s, so if you want more speed, ornith-1.5-35b-a3b-apex-mtp-i-quality is faster (~105.2 tok/s) and still scores well for coding (83.6/100).
- Is qwen35-9b good for agentic (tool-using) tasks?
- In our benchmarks, qwen35-9b scores 42.6/100 for agentic workflows. It runs at about 75.6 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 qwen35-9b for local inference?
- Across 2 community benchmark runs, qwen35-9b reaches up to 77.5 tok/s and averages 75.6 tok/s, with the fastest results on NVIDIA GeForce RTX 3080 Ti.
- How much memory does qwen35-9b need?
- The leanest observed configuration used about 10.5 GB of memory.
- Which tools have been used to run qwen35-9b?
- Benchmarks were submitted using OpenAI-compatible. Results are community-contributed and updated as new runs arrive.