Model benchmarks
qwen_coder local LLM performance
As of November 2026, qwen_coder runs at up to 42.2 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
42.2 tok/s
Average speed
41.1 tok/s
Avg PP
962.6 tok/s
Min memory
34.7 GB
Max context
65,536 tokens
Avg output / run
7,242 tokens
Avg runtime / run
3m 22s
Avg quality
66.9
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 | 66.8 | 66.9 | 67.1 |
| Agent Workflow | 57.4 | 63.0 | 68.6 |
| Code Generation | 60.6 | 62.5 | 64.4 |
| Role Play & Narrative | 68.0 | 73.6 | 79.1 |
| Research & Analysis | 66.2 | 68.7 | 71.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen_coder 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 GTX 1080 Ti | LM Studio | Q8_0 | 42.2 tok/s | 41.1 tok/s | 34.7 GB | 65,536 tokens | 67.0 | 2 |
Benchmark runs
All 2 qwen_coder runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is qwen_coder good for coding?
- In our benchmarks, qwen_coder scores 62.5/100 for coding. It runs at about 41.1 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 qwen_coder good for agentic (tool-using) tasks?
- In our benchmarks, qwen_coder scores 63.0/100 for agentic workflows. It runs at about 41.1 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 qwen_coder for local inference?
- Across 2 community benchmark runs, qwen_coder reaches up to 42.2 tok/s and averages 41.1 tok/s, with the fastest results on NVIDIA GeForce GTX 1080 Ti.
- How much memory does qwen_coder need?
- The leanest observed configuration used about 34.7 GB of memory (quantizations tested: Q8_0).
- Which tools have been used to run qwen_coder?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.