Qwen 2.5 7B instruct
QwenCompact
Tool Use
About this model
Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
Performance Tier
Compact
Qwen 2.5 7B instruct is a compact model from Qwen : optimized for speed and affordability.
Small, fast, and affordable. Optimized for speed and low cost, great for high-volume or simple tasks.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.040 |
| Output (completion) | $0.100 |
Capabilities
Context Length33K
Max Output Tokens33K
TokenizerQwen
Inputtext
Outputtext
Release DateOctober 16, 2024
Benchmarks
General Intelligence
MMLU
74.2%
Mathematics
MATH-500
65%
Programming
HumanEval
75.6%
Recommended Use Cases
General ChatCodingTranslation
Strengths
- Strong performance for a 7B parameter model
- Excellent multilingual support (29+ languages including French)
- Open-weight with Apache 2.0 license
- Very low cost ideal for high-volume deployments
Limitations
- Limited complex reasoning due to small model size
- Not suitable for advanced coding or research tasks
Resources
This model may use your data for training
