Model benchmarks
qwen3:14b local LLM performance
As of April 2026, qwen3:14b runs at up to 21.0 tok/s for local inference (best of 8 community benchmark runs across 1 GPU).
OllamaQ4_K_M
Model size
14.8B
Peak speed
21.0 tok/s
Average speed
17.1 tok/s
Min memory
9.4 GB
Max context
14,939 tokens
Best quality
93.0
Benchmark runs
8
GPUs tested
1
Performance by hardware and tool
Every hardware/tool/quantization combination qwen3:14b 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 | 21.0 tok/s | 17.1 tok/s | 9.4 GB | 14,939 tokens | 63.5 | 8 |
Frequently asked questions
- How fast is qwen3:14b for local inference?
- Across 8 community benchmark runs, qwen3:14b reaches up to 21.0 tok/s and averages 17.1 tok/s, with the fastest results on AMD Radeon RX 7900 XTX.
- How much memory does qwen3:14b need?
- The leanest observed configuration used about 9.4 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run qwen3:14b?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.