Model benchmarks
qwen3-coder:latest local LLM performance
As of April 2026, qwen3-coder:latest runs at up to 96.0 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
30.5B
Peak speed
96.0 tok/s
Average speed
64.6 tok/s
Min memory
18.9 GB
Max context
65.536 tokens
Avg quality
64.3
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 | 58.2 | 64.3 | 70.5 |
| Agent Workflow | 52.9 | 70.2 | 87.5 |
| Code Generation | 63.1 | 65.0 | 66.8 |
| Role Play & Narrative | 60.3 | 68.5 | 76.7 |
| Research & Analysis | 52.6 | 53.7 | 54.8 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen3-coder:latest has been benchmarked on, ranked by peak token generation speed. Last updated April 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7900 XTX | Ollama | Q4_K_M | 96.0 tok/s | 64.6 tok/s | 18.9 GB | 65.536 tokens | 64.3 | 2 |
Benchmark runs
All 2 qwen3-coder:latest runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is qwen3-coder:latest good for coding?
- In our benchmarks, qwen3-coder:latest scores 65.0/100 for coding. It runs at about 64.6 tok/s, so if you want more speed, unsloth/Qwen3.8-27B-GGUF:IQ3_S is faster (~104.3 tok/s) and still scores well for coding (83.0/100).
- Is qwen3-coder:latest good for agentic (tool-using) tasks?
- In our benchmarks, qwen3-coder:latest scores 70.2/100 for agentic workflows. It runs at about 64.6 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-Q4_K_S is faster (~165.0 tok/s) and still scores well for agentic workflows (89.3/100).
- How fast is qwen3-coder:latest for local inference?
- Across 2 community benchmark runs, qwen3-coder:latest reaches up to 96.0 tok/s and averages 64.6 tok/s, with the fastest results on AMD Radeon RX 7900 XTX.
- How much memory does qwen3-coder:latest need?
- The leanest observed configuration used about 18.9 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run qwen3-coder:latest?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.