Which AI models run on a PC with 32 GB of RAM and a 16 GB graphics card?
21 of Toskar's 21 models run on a PC with 32 GB of RAM and a 16 GB graphics card, and 21 of them run comfortably. A desktop with an NVIDIA GeForce RTX 4080 or 4060 Ti 16 GB, or an AMD Radeon RX 7800 XT.
Start here
The best model for each job
The largest model of each kind that runs comfortably on this computer.
Everyday chat and writing
Qwen 2.5 32BLarge high-quality model for capable machines.
Coding
Muse Glimmer 30BMeta's large model that sees pictures, codes, and reasons well; for 32 GB Macs or 24 GB graphics cards.
Pictures and screenshots
Qwen 3.8 27BThe most capable everyday assistant, for computers with plenty of memory. Sees pictures too.
Step-by-step reasoning
Qwen 2.5 14BLargest curated quality pick when your machine has headroom.
Every model on this computer
Graded with Toskar 1.12.1's own estimate: the model file plus working memory at an 8K context.
Excellent fitPlenty of memory to spare.
- Qwen 3.8 27B≈ 20.4 GB · Partial GPU offload expected
- Muse Glimmer 30B≈ 17.1 GB · Partial GPU offload expected
- Qwen 2.5 14B≈ 10.2 GB · Good GPU fit
- Qwen 2.5 Coder 14B≈ 9.7 GB · Good GPU fit
- Qwen 3.5 9B≈ 7.2 GB · Good GPU fit
- Gemma 2 9B≈ 6.5 GB · Good GPU fit
- Qwen 2.5 VL 7B≈ 6.1 GB · Good GPU fit
- Qwen 2.5 Coder 7B≈ 5.3 GB · Good GPU fit
- Qwen 2.5 7B≈ 5.3 GB · Good GPU fit
- DeepSeek R1 Distill 7B≈ 5.3 GB · Good GPU fit
- Mistral 7B Instruct≈ 5.0 GB · Good GPU fit
- Qwen 3.5 4B≈ 3.9 GB · Good GPU fit
- Gemma 3 4B≈ 3.9 GB · Good GPU fit
- Phi 3.5 Mini≈ 3.0 GB · Good GPU fit
- Llama 3.2 3B≈ 2.6 GB · Good GPU fit
- Qwen 2.5 3B≈ 2.5 GB · Good GPU fit
- Gemma 2 2B≈ 2.2 GB · Good GPU fit
- Qwen 2.5 Coder 1.5B≈ 1.6 GB · Good GPU fit
- DeepSeek R1 Distill 1.5B≈ 1.6 GB · Good GPU fit
- Llama 3.2 1B≈ 1.3 GB · Good GPU fit
Good fitShould run comfortably.
- Qwen 2.5 32B≈ 21.5 GB · Partial GPU offload expected
Questions
- What's the best local AI model for a PC with 32 GB of RAM and a 16 GB graphics card?
- For everyday use, start with Qwen 2.5 32B: it's the largest of its kind that runs comfortably here. For coding, try Muse Glimmer 30B. For pictures and screenshots, try Qwen 3.8 27B. For step-by-step reasoning, try Qwen 2.5 14B.
- How big a model can a PC with 32 GB of RAM and a 16 GB graphics card run?
- The largest that runs is Qwen 2.5 32B, at about 21.5 GB; the largest that runs comfortably is Qwen 2.5 32B, at about 21.5 GB. Memory decides it: the model and the conversation have to fit, with room left for everything else you have open.
- Do I need a graphics card?
- It helps a lot. 18 of these models fit entirely in the card's 16.0 GB, which is the fastest way to run them. Larger ones run partly on the card and partly on the processor.
- Does it cost anything to run these models?
- No. Toskar Core is free and open source, and the models download at no cost. Everything runs on your own computer, so there's no subscription and no per-question bill.
Other computers
Mac with Apple silicon
PC with a graphics card
- PC, 16 GB + 8 GB graphics card
- PC, 32 GB + 12 GB graphics card
- PC, 32 GB + 16 GB graphics card
- PC, 64 GB + 24 GB graphics card
Run them with Toskar
Toskar Core is free and open source for Mac, Windows, and Linux. It suggests the models that fit your computer, downloads them for you, and keeps every question on your computer.