Alibaba · Strong multilingual support
Qwen 2.5 1.5B on iPhone
- Balanced
Qwen 2.5 1.5B is Alibaba’s mid-size open model, and in Priobs it is the go-to for chatting in more than one language. It runs on your iPhone with no internet after the download.
Free download · iPhone, iOS 26.0 or later
Specifications
- Company
- Alibaba
- Parameters
- 1.5B
- Download size
- 878 MB
- Minimum RAM
- 1.2 GB
- Category
- Balanced
- Tools
- Not supported
- License
- Apache 2.0
- Format
- 4-bit quantized, MLX
Numbers come straight from the model catalogue inside the app. Qwen 2.5 1.5B and its licence belong to Alibaba.
About Qwen 2.5 1.5B
What is Qwen 2.5 1.5B?
Qwen 2.5 1.5B is the step up from Qwen 2.5 0.5B: 1.5 billion parameters, trained with a strong focus on multilingual data. In Priobs it runs as a 4-bit quantized MLX build that stays fast and light.
Who made it
Alibaba builds Qwen as an open model family in many sizes, with multilingual skill as a core strength. Qwen 2.5 1.5B ships under the Apache 2.0 licence.
What it’s good at on iPhone
Qwen 2.5 1.5B is the pick for strong multilingual support:
- Chatting in languages beyond English, more fluently than the 0.5B model
- Translating and explaining text across languages
- Everyday chat with more depth than the smallest models
- A light footprint that fits most iPhones
Qwen 2.5 1.5B does not use Priobs tools. For calendar, reminders or Health, pick a model marked Tools.
It sits between Qwen 2.5 0.5B and bigger models like Llama 3.2 3B: faster and smaller than Llama, with a multilingual edge.
Which iPhones can run it
Qwen 2.5 1.5B needs at least 1.2 GB of memory. Priobs checks your iPhone, hides models it does not have the memory for, and warns you if a model is close to the limit and may be unstable. Every iPhone that runs iOS 26 has more than that.
Setup
How to get it in Priobs.
One download over Wi-Fi and you are offline-ready for good.
Open Priobs and go to the Model Library.
Find Qwen 2.5 1.5B and tap Download (878 MB).
Select it as your active model and start chatting offline.
FAQ
Qwen 2.5 1.5B, answered.
Is Qwen 2.5 1.5B better than Qwen 2.5 0.5B?
What languages does Qwen 2.5 1.5B handle well?
Does Qwen 2.5 1.5B support tools?
Is Qwen 2.5 1.5B good for writing long documents?
Does Qwen 2.5 1.5B need an internet connection?
Other models
You can keep several installed at once.
Switching models takes one tap. A common setup: a small, fast model for quick questions and a bigger one for anything that needs more depth.
Qwen 2.5 0.5B
Alibaba
FastestFastest responses, good for simple tasks
288 MB · 512 MB RAM
LFM2 1.2B
Liquid AI
FastestToolsBuilt for speed on phones, snappy short replies
663 MB · 862 MB RAM
Gemma 3 1B
Google
BalancedBalanced speed and quality
767 MB · 1 GB RAM
Qwen 3 1.7B
Alibaba
BalancedToolsReasoningCompact model that thinks before answering
982 MB · 1.2 GB RAM
Llama 3.2 3B
Meta
BalancedToolsGreat for writing and everyday questions
1.8 GB · 2.3 GB RAM
Phi-4 Mini 3.8B
Microsoft
BalancedTools (beta)Strong at math and step-by-step answers
2.2 GB · 2.8 GB RAM
Qwen 3 4B
Alibaba
Most CapableToolsReasoningMost capable, best for complex tasks
2.3 GB · 2.9 GB RAM
Qwen 3 4B Thinking
Alibaba
Most CapableTools (beta)ReasoningWorks through problems step by step, slower to answer
2.3 GB · 2.9 GB RAM
Gemma 4 E2B
Google
BalancedTools (beta)Google’s latest with strong reasoning
3.6 GB · 4.5 GB RAM
Apple Intelligence
Apple
Built inToolsBuilt into your iPhone, nothing to download
No download, built into iOS