← Back to Models
Alibabatransformer
Qwen2.5 Coder 14B
14B parameters • 8.5GB VRAM (Q4 estimate) • 131,072 context
Estimate · Q4_K_M · 4k context · batch 1. For dense 7B–70B this sits ~5–8% above the Q4_K_M GGUF file. Not peak runtime VRAM and not a measured bench.
Specifications
Parameters
14B
VRAM (Q4 est.)
8.5 GB
VRAM (FP16)
28 GB
Context Window
131,072
Architecture
transformer
License
Apache-2.0
Finding cloud alternatives...
Run Qwen2.5 Coder 14B on RTX 3080 10GB
~8.5GB VRAM needed at Q4. RTX 3080 10GB has 10GB — buy hardware or rent cloud.
We may earn a commission from cloud and hardware partners at no extra cost to you.
Find the cheapest GPU that can run Qwen2.5 Coder 14B
Compatibility Lab — check every GPU × quantization combination