Qwen Models: Local AI on Any Device
Qwen by Alibaba Cloud offers the most versatile range of open-weight models available today. With variants from 0.5B to 235B parameters, there is a Qwen model for every device, from iPhones with 6GB RAM to Mac Studios with 192GB. Qwen consistently scores among the top models for coding, chat, and multilingual tasks.
Alibaba Cloud20 local models
DEVELOPER
Alibaba Cloud
MODELS
20
SIZE RANGE
0.5B–235B
RAM RANGE
2–192 GB
Key Features
Widest size range (0.5B to 235B)
Strong multilingual and coding performance
Best quality/size ratio in the 7B-14B range
Works on devices from iPhones to Mac Studios
All Qwen Models
| Model | Size | Quant | VRAM | Min RAM | Best For | Quality | Ollama |
|---|---|---|---|---|---|---|---|
| Qwen2.5 0.5B Instruct | 0.5B | Q4_K_M | 0.8 GB | 2 GB | Chat, Mobile | 45 | |
| Qwen3.5 0.8B Instruct | 0.8B | Q4_K_M | 0.8 GB | 2 GB | Chat, Mobile | 55 | |
| Qwen2.5 1.5B Instruct | 1.5B | Q4_K_M | 1.5 GB | 4 GB | Chat, Translation | 58 | |
| Qwen3.5 2B Instruct | 2B | Q4_K_M | 1.8 GB | 4 GB | Chat, Edge tasks | 68 | |
| Qwen2.5 3B Instruct | 3B | Q4_K_M | 2.5 GB | 6 GB | Chat, Coding | 66 | |
| Qwen3.5 4B Instruct | 4B | Q4_K_M | 3.5 GB | 8 GB | Coding, Agents, Multimodal | 82 | |
| Qwen2.5 7B Instruct | 7B | Q4_K_M | 5.5 GB | 10 GB | Chat, Coding | 79 | |
| Qwen2.5 Coder 7B | 7B | Q4_K_M | 5.5 GB | 10 GB | Coding | 83 | |
| Qwen3 8B | 8B | Q4_K_M | 6.5 GB | 12 GB | Chat, Coding | 84 | |
| Qwen3.5 9B Instruct | 9B | Q4_K_M | 7 GB | 14 GB | Quality, Coding, Reasoning | 90 | |
| Qwen2.5 14B Instruct | 14B | Q4_K_M | 11 GB | 20 GB | Coding, Chat | 90 | |
| Qwen2.5 Coder 14B | 14B | Q4_K_M | 11 GB | 22 GB | Coding | 93 | |
| Qwen3 14B | 14B | Q4_K_M | 11 GB | 20 GB | Coding, Quality | 91 | |
| Qwen3.5 27B Instruct | 27B | Q4_K_M | 16 GB | 20 GB | Chat, Coding, Complex reasoning | 90 | |
| Qwen3.6 27B | 27B | Q4_K_M | 18 GB | 24 GB | Coding, Quality, Long context | 94 | |
| Qwen3 30B | 30B | Q4_K_M | 22 GB | 28 GB | Quality, Coding | 95 | |
| Qwen3.5 35B-A3B Instruct | 35B | Q4_K_M | 20 GB | 24 GB | Reasoning, Coding, Agent scenarios | 92 | |
| Qwen3.6 35B-A3B | 35B | Q4_K_M | 22 GB | 24 GB | Reasoning, Coding, Agents | 93 | |
| Qwen3.5 122B-A10B Instruct | 122B | Q4_K_M | 72 GB | 96 GB | Frontier-level reasoning, Complex tasks | 96 | |
| Qwen3 235B A22B | 235B | Q4_K_M | 130 GB | 192 GB | Quality, Reasoning | 98 |
Device Compatibility
Which Qwen models can run on each device class, based on minimum RAM requirements.
| Model | iPhone | Air | Pro | Studio | Mini |
|---|---|---|---|---|---|
| Qwen2.5 0.5B Instruct (0.5B) | Excellent | Excellent | Excellent | Excellent | Excellent |
| Qwen3.5 0.8B Instruct (0.8B) | Excellent | Excellent | Excellent | Excellent | Excellent |
| Qwen2.5 1.5B Instruct (1.5B) | Excellent | Excellent | Excellent | Excellent | Excellent |
| Qwen3.5 2B Instruct (2B) | Excellent | Excellent | Excellent | Excellent | Excellent |
| Qwen2.5 3B Instruct (3B) | Possible | Possible | Excellent | Excellent | Excellent |
| Qwen3.5 4B Instruct (4B) | Possible | Possible | Excellent | Excellent | Excellent |
| Qwen2.5 7B Instruct (7B) | Possible | Possible | Excellent | Excellent | Excellent |
| Qwen2.5 Coder 7B (7B) | Possible | Possible | Excellent | Excellent | Excellent |
| Qwen3 8B (8B) | Possible | Possible | Possible | Excellent | Possible |
| Qwen3.5 9B Instruct (9B) | No | Possible | Possible | Excellent | Possible |
| Qwen2.5 14B Instruct (14B) | No | Possible | Possible | Excellent | Possible |
| Qwen2.5 Coder 14B (14B) | No | Possible | Possible | Excellent | Possible |
| Qwen3 14B (14B) | No | Possible | Possible | Excellent | Possible |
| Qwen3.5 27B Instruct (27B) | No | Possible | Possible | Excellent | Possible |
| Qwen3.6 27B (27B) | No | Possible | Possible | Possible | Possible |
| Qwen3 30B (30B) | No | Possible | Possible | Possible | Possible |
| Qwen3.5 35B-A3B Instruct (35B) | No | Possible | Possible | Possible | Possible |
| Qwen3.6 35B-A3B (35B) | No | Possible | Possible | Possible | Possible |
| Qwen3.5 122B-A10B Instruct (122B) | No | No | Possible | Possible | No |
| Qwen3 235B A22B (235B) | No | No | No | Possible | No |
RAM Requirements
0.8 GB · min 2 GB
0.8 GB · min 2 GB
1.5 GB · min 4 GB
1.8 GB · min 4 GB
2.5 GB · min 6 GB
3.5 GB · min 8 GB
5.5 GB · min 10 GB
5.5 GB · min 10 GB
6.5 GB · min 12 GB
7 GB · min 14 GB
11 GB · min 20 GB
11 GB · min 22 GB
11 GB · min 20 GB
16 GB · min 20 GB
18 GB · min 24 GB
22 GB · min 28 GB
20 GB · min 24 GB
22 GB · min 24 GB
72 GB · min 96 GB
130 GB · min 192 GB
Frequently Asked Questions
What is the best Qwen model for 16GB RAM?
Qwen2.5 7B Q4 is the sweet spot for 16GB RAM. It uses about 5.5GB, leaving room for your OS and apps. For coding tasks, it performs close to models twice its size.
Can I run Qwen on an iPhone?
Yes. Qwen2.5 0.5B and 1.5B models run on iPhones with 6GB+ RAM. They are fast enough for basic chat and translation, though quality is limited by their small size.
How does Qwen compare to Llama 3?
Qwen offers more size options (0.5B to 235B vs Llama's 1B to 405B). At 7B, Qwen2.5 edges out Llama 3.2 on coding benchmarks, while Llama tends to be stronger at general reasoning.
What Ollama command runs Qwen?
Run `ollama run qwen2.5:7b-instruct-q4_K_M` for the most popular size. Replace `7b` with `1.5b`, `14b`, `32b`, or `72b` depending on your RAM.