Skip to content

Qwen 2.5 14B

Apache 2.0

Alibaba · 14B · transformer-decoder

2024-09-19131K context14B params

Use Cases

chatcodereasoningmultilingualmathsummary

Quantization Options

QuantBitsVRAMQualityStatus
Q4_K_Mrec49.9 GBGood
Q5_K_M511.3 GBGood
Q8_0816.0 GBExcellent

About this model

Qwen 2.5 14B is a strong mid-to-large model from Alibaba's Qwen 2.5 series, offering significantly improved reasoning and coding capabilities over its 7B counterpart. It supports 128K context and excels at complex instruction following. This model fits well on GPUs with 16-24GB VRAM at common quantization levels, making it accessible to users with high-end consumer hardware. It is particularly strong at mathematical reasoning and structured output generation.

Benchmarks

79.9
mmlu