Local AI models
What AI models can my computer run?
Running AI on your own computer comes down to memory. Pick yours to see which of Toskar's 21 models fit, with the same estimate the app uses. How memory decides what runs
Check your computer
Your computer
Memory (unified)
Find it under Apple menu > About This Mac. On Apple silicon the graphics share this memory.
20 of 21 models run on this computer, 18 of them comfortably.
Excellent fitPlenty of memory to spare.
- Qwen 2.5 14Breasoning≈ 10.2 GB
- Qwen 2.5 Coder 14Bcoding≈ 9.7 GB
- Qwen 3.5 9Bvision≈ 7.2 GB
- Gemma 2 9B≈ 6.5 GB
- Qwen 2.5 VL 7Bvision≈ 6.1 GB
- Qwen 2.5 Coder 7Bcoding≈ 5.3 GB
- Qwen 2.5 7B≈ 5.3 GB
- DeepSeek R1 Distill 7Breasoning≈ 5.3 GB
- Mistral 7B Instruct≈ 5.0 GB
- Qwen 3.5 4Bvisionfast≈ 3.9 GB
- Gemma 3 4Bvision≈ 3.9 GB
- Phi 3.5 Minireasoning≈ 3.0 GB
- Llama 3.2 3B≈ 2.6 GB
- Qwen 2.5 3B≈ 2.5 GB
- Gemma 2 2Bfast≈ 2.2 GB
- Qwen 2.5 Coder 1.5Bcodingfast≈ 1.6 GB
- DeepSeek R1 Distill 1.5Breasoningfast≈ 1.6 GB
- Llama 3.2 1Bfast≈ 1.3 GB
May run slowlyMay need swap or a shorter context.
- Qwen 3.8 27Bvision≈ 20.4 GB
- Muse Glimmer 30Breasoningvision≈ 17.1 GB
Too big for this computer: Qwen 2.5 32B. A paired computer with more memory can run them for you.
Estimates use Toskar 1.12.1's own sizing: the model file plus working memory at an 8K context. Once a model has run, Toskar measures it on your computer and uses that instead.
By computer
Which models run on my computer?
Mac with Apple silicon
PC with a graphics card
By model
Can my computer run this model?
The memory each model needs, smallest first.
- 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
- Muse Glimmer 30B≈ 17.1 GB
- Qwen 3.8 27B≈ 20.4 GB
- Qwen 2.5 32B≈ 21.5 GB
Run them with Toskar
Toskar Core is free and open source for Mac, Windows, and Linux. It suggests the models that fit your computer and downloads them for you, and nothing you ask leaves your computer.