CanMyPCRunAILocal AI compatibility
Check my PC

What AI models can you run with 32GB of VRAM?

With 32GB of VRAM, 194 of 228 models from the Ollama library run entirely on the GPU at 4K context. 10 more run by offloading part of the model to system RAM, which works but is slower.

194

run well

10

with trade-offs

228

models tested

Check my actual PC

Best AI models for 32GB of VRAM

Heaviest first — each of these fits entirely in 32GB at 4K context, counting weights, KV cache, compute buffers and runtime overhead.

Models that fit in 32GB of VRAM
ModelBuildMemory neededVerdict
laguna-xs-2.1latest~27.4 GBGood fit
codebooga34B~27.3 GBGood fit
phind-codellama34B~27.3 GBGood fit
qwq32B~26.8 GBGood fit
command-r35B~26.8 GBGood fit
olmo-3.132B~26.3 GBGood fit
glm-4.7-flashlatest~25.7 GBGood fit
north-mini-code-1.0latest~25.2 GBGood fit
qwen3-coder30B~25.1 GBGood fit
qwen3.627B~23.6 GBGood fit
qwen3.827B~22.8 GBExcellent fit
muse-glimmer30B~22.7 GBExcellent fit
mistral-small3.124B~21.0 GBExcellent fit
devstral-small-224B~20.6 GBExcellent fit
mistral-small3.224B~20.6 GBExcellent fit
lfm224B~19.6 GBExcellent fit
devstral24B~19.5 GBExcellent fit
magistral24B~19.5 GBExcellent fit
gpt-oss20B~18.8 GBExcellent fit
gpt-oss-safeguard20B~18.8 GBExcellent fit
mistral-small22B~18.2 GBExcellent fit
codestral22B~18.2 GBExcellent fit
solar-pro22B~18.1 GBExcellent fit
phi4-reasoning14B~15.2 GBExcellent fit
deepseek-coder-v216B~14.2 GBExcellent fit

Graphics cards with 32GB of VRAM

GeForce RTX 5090

How this was calculated

Every model is evaluated at 4K context against 32GB of VRAM, minus a reserve for the display and operating system, and assuming 32GB of system RAM with working GPU drivers. Your own machine may differ, which is what the PC scan measures directly.

32GB VRAM and local AI — frequently asked questions

Is 32GB of VRAM enough to run AI models locally?
Yes — 194 of the 228 models tested run entirely on the GPU with 32GB at 4K context, and 10 more run with part of the model offloaded to system RAM. The heaviest that fits is laguna-xs-2.1:latest, needing about 27.4 GB.
What is the best AI model for 32GB VRAM?
For maximum capability, laguna-xs-2.1 (laguna-xs-2.1:latest) is the heaviest build that still fits entirely in 32GB. Smaller models leave headroom for a longer context window, which often matters more than raw parameter count.
Which graphics cards have 32GB of VRAM?
Cards with 32GB include GeForce RTX 5090.

Other VRAM amounts

4GB6GB8GB10GB12GB16GB24GB