Skip to content

Qwen 3 14B

Apache 2.0

Alibaba · 14B · transformer-decoder

2025-04-29 131K context 14B params

Use Cases

chat code reasoning multilingual math tools writing summary

Quantization Options

QuantBitsVRAMQualityStatus
Q4_K_Mrec412.0 GBGood
Q8_0819.0 GBExcellent
F161633.0 GBExcellent

About this model

Qwen 3 14B is one of the strongest mid-range models available, excelling at coding, math, reasoning, and creative tasks. Hybrid thinking mode lets it match the performance of much larger models on complex problems while staying fast on simple ones. At Q4 it fits on 16 GB GPUs or Macs, making it a top pick for the RTX 4060 Ti 16GB, RTX 5070 Ti, or M-series Macs with 16 GB. A strong contender for the best daily driver at this VRAM tier.

Benchmarks

80.5
mmlu