Qwen2.5 7B Instruct
Summary
Qwen2.5 7B Instruct is an open-weight language model from Alibaba (Qwen), released on Sept 2024. It accepts text and generates text, with a 131K-token context window and up to 8K output tokens per response. As of 21 Oct 2026, the lowest listed API price is $0.05 per million input tokens and $0.05 per million output tokens (SiliconFlow), across 2 providers we track. Alibaba (Qwen) has deprecated this model.
Qwen instruction model for multilingual chat, reasoning, and tool use
Last verified 21 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | Sept 2024 [models.dev] |
| Status | Deprecated [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 7.6B [Hugging Face] |
| Context window | 131K (131,072 tokens) [models.dev] |
| Max output | 8K tokens [models.dev] |
| Knowledge cutoff | Apr 2024 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | Yes [models.dev] |
| Hugging Face | Qwen/Qwen2.5-7B-Instruct [Hugging Face] |
Qwen2.5 7B Instruct API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| SiliconFlow Qwen/Qwen2.5-7B-Instruct | $0.05 | $0.05 | – | 33K | models.dev, 21 Oct 2026 |
| OpenRouter qwen/qwen-2.5-7b-instruct | $0.10 | $0.20 | – | 33K | OpenRouter, 21 Oct 2026 |
Running Qwen2.5 7B Instruct locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 4.6 GB | 5.9 GB | 7.3 GB |
| Q8_0 (8-bit) | 8.1 GB | 9.4 GB | 11 GB |
| FP16 / BF16 (16-bit) | 15 GB | 17 GB | 18 GB |
At 4-bit with an 8K conversation, Qwen2.5 7B Instruct needs about 5.9 GB, so it fits on a graphics card with 8 GB or more, such as the NVIDIA GeForce RTX 4060 8 GB. Check your own hardware, or see Running local LLMs on an 8 GB GPU on our sister site AIPCs.
Frequently asked questions
What is the context window of Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct has a context window of 131,072 tokens (131K) and can generate up to 8,192 tokens in a single response, according to models.dev.
How much does the Qwen2.5 7B Instruct API cost?
Qwen2.5 7B Instruct is listed from $0.05 per million input tokens and $0.05 per million output tokens (SiliconFlow). Prices last verified 21 Oct 2026.
Is Qwen2.5 7B Instruct open source?
Qwen2.5 7B Instruct is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen2.5-7B-Instruct under the apache-2.0 license. Check the license terms before commercial use.
When was Qwen2.5 7B Instruct released?
Alibaba (Qwen) released Qwen2.5 7B Instruct on Sept 2024, according to models.dev.
Which providers offer Qwen2.5 7B Instruct?
We track Qwen2.5 7B Instruct on 2 providers: SiliconFlow, OpenRouter.
How much VRAM does Qwen2.5 7B Instruct need?
About 5.9 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 9.4 GB at 8-bit. The 4-bit model fits on a graphics card with 8 GB or more, such as the NVIDIA GeForce RTX 4060 8 GB. These are estimates from the model's published parameter count and architecture.
Change history
- License changed from none to apache-2.0
- Parameter count changed from none to 7.6B
- Now listed on OpenRouter
- Added to the directory
- Now listed on SiliconFlow