Qwen 2.5 Coder 7B
by Alibaba · qwen-2.5 family
7B
parameters
text-generation code-generation
Qwen 2.5 Coder 7B is Alibaba's dedicated code-generation model, fine-tuned from the Qwen 2.5 base for exceptional performance on programming tasks. It supports 92+ programming languages and excels at code completion, generation, repair, and reasoning. This model achieves coding benchmark scores that rival much larger general-purpose models, making it an outstanding choice for developers seeking a local coding assistant. Its 128K context window allows it to process entire codebases effectively.
Quick Start with Ollama
ollama run 7b-instruct-q8_0 | Creator | Alibaba |
| Parameters | 7B |
| Architecture | transformer-decoder |
| Context | 128K tokens |
| Released | Nov 12, 2024 |
| License | Apache 2.0 |
| Ollama | qwen2.5-coder |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M | 3.5 GB | 5.7 GB | | 7b-instruct-q4_K_M |
| Q8_0 rec | 6.3 GB | 9 GB | | 7b-instruct-q8_0 |
| F16 | 13.3 GB | 16 GB | | 7b-instruct-fp16 |
Compatible Hardware
Q8_0 requires 9 GB VRAM
Benchmark Scores
68.0
mmlu