Qwen 2.5 14B
AlibabaMid-range powerhouse from Alibaba with exceptional coding benchmarks. Great balance of capability and resource requirements for serious development work.
Parameters 14B
Min VRAM 10 GB
Recommended VRAM 16 GB
Context Length 128K
License Apache 2.0
🚀 Get Started
Run Qwen 2.5 14B locally with one command:
ollama run qwen2.5:14b Requires Ollama installed.
📊 Benchmarks
BenchmarkScore
MMLU 79.9
GSM8K 89.2
HumanEval 80.5
💻 Hardware Recommendations
🟢 Minimum
10 GB VRAM GPU or 20+ GB RAM (CPU mode)
Expect slower generation in CPU mode
🔵 Recommended
16 GB VRAM GPU
Fast generation with room for context