Can my computer run Qwen 3.6 35B-A3B?
A large mixture of experts that runs fast for its size: each word uses 3B of its 35B parameters. Sees pictures too. Qwen 3.6 35B-A3B needs about 21.8 GB of memory. It runs comfortably on Macs with 32 GB or more, and on PCs with 32 GB of RAM or more, even without a graphics card.
Qwen 3.6 35B-A3B on common computers
Graded with Toskar 1.14.0's own estimate: the model file plus working memory at an 8K context.
| Computer | Fit | What to expect |
|---|---|---|
| Mac, 8 GB | Too big | Needs more memory than this computer has. |
| Mac, 16 GB | Too big | Needs more memory than this computer has. |
| Mac, 24 GB | Tight fit | Runs, with little memory to spare. Close other big apps. |
| Mac, 32 GB | Good fit | Should run comfortably. |
| Mac, 48 GB | Excellent fit | Plenty of memory to spare. |
| Mac, 64 GB | Excellent fit | Plenty of memory to spare. |
| Mac, 128 GB | Excellent fit | Plenty of memory to spare. |
| PC, 8 GB, no graphics card | Too big | Needs more memory than this computer has. |
| PC, 16 GB, no graphics card | Too big | Needs more memory than this computer has. |
| PC, 32 GB, no graphics card | Good fit | Should run comfortably. |
| PC, 16 GB + 8 GB graphics card | Too big | Needs more memory than this computer has. |
| PC, 32 GB + 12 GB graphics card | Good fit | Should run comfortably. Partial GPU offload expected. |
| PC, 32 GB + 16 GB graphics card | Good fit | Should run comfortably. Partial GPU offload expected. |
| PC, 64 GB + 24 GB graphics card | Excellent fit | Plenty of memory to spare. Good GPU fit. |
About Qwen 3.6 35B-A3B
- Memory needed
- ≈ 21.8 GB
- Download size
- 19.1 GB
- Parameters
- 35B
- Quantization
- Q4_K_M
- Longest conversation
- 256K tokens
Good at
- Chat and writing
- Coding
- Sees pictures and screenshots
- Uses tools, such as web search and your files
Languages it handles well
English, Simplified Chinese, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic
Similar models to compare
- Qwen 2.5 32B≈ 21.5 GB
Large high-quality model for capable machines.
- Qwen 3.8 27B≈ 20.4 GB
The most capable everyday assistant, for computers with plenty of memory. Sees pictures too.
- Muse Glimmer 30B≈ 17.1 GB
Meta's large model that sees pictures, codes, and reasons well; for 32 GB Macs or 24 GB graphics cards.
- gpt-oss 20B≈ 13.1 GB
OpenAI's open model: thinks before it answers and uses tools, fast for its size.
Questions
- How much memory does Qwen 3.6 35B-A3B need?
- About 21.8 GB with Toskar's default 8K context: the 19.1 GB model file plus room for the conversation. After it has run once, Toskar measures what it really uses on your computer.
- Can Qwen 3.6 35B-A3B run on a Mac with 8 GB?
- No. It needs about 21.8 GB, more than a Mac with 8 GB has. A smaller model, or a paired computer with more memory, can answer instead.
- Can Qwen 3.6 35B-A3B run without a graphics card?
- It needs more memory than most PCs without a graphics card have. No. It needs about 21.8 GB, more than a PC with 16 GB of RAM and no graphics card has. A smaller model, or a paired computer with more memory, can answer instead.
- Is Qwen 3.6 35B-A3B free to use?
- Yes. Toskar Core is free and open source, and it downloads Qwen 3.6 35B-A3B for you at no cost. Everything runs on your computer, so there's no per-question bill.
Every model
- Llama 3.2 1B≈ 1.3 GB
- Qwen 2.5 Coder 1.5B≈ 1.6 GB
- DeepSeek R1 Distill 1.5B≈ 1.6 GB
- Gemma 2 2B≈ 2.2 GB
- Qwen 2.5 3B≈ 2.5 GB
- Llama 3.2 3B≈ 2.6 GB
- Phi 3.5 Mini≈ 3.0 GB
- Gemma 3 4B≈ 3.9 GB
- Qwen 3.5 4B≈ 3.9 GB
- Mistral 7B Instruct≈ 5.0 GB
- Qwen 2.5 Coder 7B≈ 5.3 GB
- Qwen 2.5 7B≈ 5.3 GB
- DeepSeek R1 Distill 7B≈ 5.3 GB
- Qwen 2.5 VL 7B≈ 6.1 GB
- Gemma 2 9B≈ 6.5 GB
- Qwen 3.5 9B≈ 7.2 GB
- Qwen 2.5 Coder 14B≈ 9.7 GB
- Qwen 2.5 14B≈ 10.2 GB
- gpt-oss 20B≈ 13.1 GB
- Muse Glimmer 30B≈ 17.1 GB
- Qwen 3.8 27B≈ 20.4 GB
- Qwen 2.5 32B≈ 21.5 GB
- Qwen 3.6 35B-A3B≈ 21.8 GB
- gpt-oss 120B≈ 66.7 GB
Run Qwen 3.6 35B-A3B with Toskar
Toskar Core is free and open source for Mac, Windows, and Linux. It checks what your computer can run, downloads the model for you, and keeps every question on your computer.