Qwen 2.5 Coder 14B
by Alibaba · qwen-2.5 family
14B
parameters
text-generation code-generation
Qwen 2.5 Coder 14B is the mid-range code specialist in Alibaba's Qwen 2.5 Coder lineup. It supports 128K context and excels at code generation, completion, debugging, and refactoring across dozens of programming languages. At Q4 it fits on 16 GB GPUs — a strong coding assistant for developers with RTX 4060 Ti 16GB or similar hardware. Competitive with much larger general-purpose models on coding benchmarks.
Quick Start with Ollama
ollama run 14b-instruct-q4_K_M | Creator | Alibaba |
| Parameters | 14B |
| Architecture | transformer-decoder |
| Context | 128K tokens |
| Released | Nov 12, 2024 |
| License | Apache 2.0 |
| Ollama | qwen2.5-coder:14b |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M rec | 9 GB | 12 GB | | 14b-instruct-q4_K_M |
| Q8_0 | 15.7 GB | 19 GB | | 14b-instruct-q8_0 |
| F16 | 29 GB | 33 GB | | 14b-instruct-fp16 |
Compatible Hardware
Q4_K_M requires 12 GB VRAM
Benchmark Scores
72.0
mmlu