Skip to content
AI Stack Nest
Open weightschatcoding

Qwen2.5 7B Instruct

Multilingual chat and coding on a laptop

Specifications

Qwen2.5 7B Instruct specifications
PropertyValue
MakerAlibaba Cloud
FamilyQwen
Parameters7.6B
Context window32K (128K with YaRN)
LicenseApache 2.0
Commercial useYes (Apache 2.0 for this size)
Best forMultilingual chat and coding on a laptop
Last verified17 Nov 2026

Memory needed to run Qwen2.5 7B Instruct

Memory by precision
PrecisionMemory (GB)
Ollama default download6.2 GB

Check your own computer with the will-it-run checker.

What it is

Qwen2.5 is a model family from Alibaba Cloud. The 7B Instruct model has about 7.61 billion parameters and supports more than 29 languages according to its model card.

Context length

The card says the default context is 32,768 tokens, and up to 131,072 tokens when you enable YaRN scaling.

Sizes and license

The family ranges from 0.5B (about 398 MB on Ollama) to 72B (about 47 GB). Most sizes use Apache 2.0, but the 3B and 72B sizes use the Qwen license instead, so check the size you pick.

How to run it

Run ollama run qwen2.5.

About these notes

Sizes, context length and license were read from the Ollama library page and the Hugging Face model card on 2026-11-17. We have not benchmarked this model ourselves, so we give no speed or quality scores.

Guides and projects using Qwen2.5 7B Instruct

More models

Official source: model card. Figures come from the vendor and our own tests; always confirm on the model card before building on a model.