Qwen 2.5 7B
by Alibaba · qwen-2.5 family
7B
parameters
text-generation code-generation multilingual math summarization
Qwen 2.5 7B is Alibaba's versatile mid-range model from the Qwen 2.5 series. It supports 128K context and delivers strong performance across text generation, coding, and mathematical reasoning, with particular strength in multilingual tasks spanning 29+ languages. This model offers an excellent balance of capability and efficiency, running smoothly on consumer GPUs. It is especially competitive in Chinese-English bilingual scenarios and structured output generation.
Quick Start with Ollama
ollama run 7b-instruct-q8_0 | Creator | Alibaba |
| Parameters | 7B |
| Architecture | transformer-decoder |
| Context Length | 128K tokens |
| License | Apache 2.0 |
| Released | Sep 19, 2024 |
| Ollama | qwen2.5 |
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 recommended | 6.3 GB | 9 GB |
★
★
★
★
★
| 7b-instruct-q8_0 |
| F16 | 13.3 GB | 16 GB |
★
★
★
★
★
| 7b-instruct-fp16 |
Compatible Hardware for Q8_0
Showing compatibility for the recommended quantization (Q8_0, 9 GB VRAM).
Compatible Hardware
Benchmark Scores
74.2
mmlu