CanMyPCRunAILocal AI compatibility
Check my PC

What AI models can you run with 24GB of VRAM?

With 24GB of VRAM, 182 of 228 models from the Ollama library run entirely on the GPU at 4K context. 22 more run by offloading part of the model to system RAM, which works but is slower.

182

run well

22

with trade-offs

228

models tested

Check my actual PC

Best AI models for 24GB of VRAM

Heaviest first — each of these fits entirely in 24GB at 4K context, counting weights, KV cache, compute buffers and runtime overhead.

Models that fit in 24GB of VRAM
ModelBuildMemory neededVerdict
mistral-small3.124B~21.0 GBGood fit
devstral-small-224B~20.6 GBGood fit
mistral-small3.224B~20.6 GBGood fit
lfm224B~19.6 GBGood fit
devstral24B~19.5 GBGood fit
magistral24B~19.5 GBGood fit
gpt-oss20B~18.8 GBGood fit
gpt-oss-safeguard20B~18.8 GBGood fit
mistral-small22B~18.2 GBGood fit
codestral22B~18.2 GBGood fit
solar-pro22B~18.1 GBGood fit
phi4-reasoning14B~15.2 GBExcellent fit
deepseek-coder-v216B~14.2 GBExcellent fit
deepseek-v216B~14.2 GBExcellent fit
phi414B~12.4 GBExcellent fit
everythinglm13B~10.9 GBExcellent fit
nexusraven13B~10.9 GBExcellent fit
open-orca-platypus213B~10.9 GBExcellent fit
codeup13B~10.9 GBExcellent fit
wizard-vicuna13B~10.9 GBExcellent fit
wizardlm-uncensored13B~10.9 GBExcellent fit
llama3.2-vision11B~10.8 GBExcellent fit
mistral-nemo12B~10.3 GBExcellent fit
gemma4e2b-it-q4_K_M~9.9 GBExcellent fit
falcon211B~9.5 GBExcellent fit

Graphics cards with 24GB of VRAM

GeForce RTX 4090GeForce RTX 3090Radeon RX 7900 XTX

How this was calculated

Every model is evaluated at 4K context against 24GB 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.

24GB VRAM and local AI — frequently asked questions

Is 24GB of VRAM enough to run AI models locally?
Yes — 182 of the 228 models tested run entirely on the GPU with 24GB at 4K context, and 22 more run with part of the model offloaded to system RAM. The heaviest that fits is mistral-small3.1:24b, needing about 21.0 GB.
What is the best AI model for 24GB VRAM?
For maximum capability, mistral-small3.1 (mistral-small3.1:24b) is the heaviest build that still fits entirely in 24GB. Smaller models leave headroom for a longer context window, which often matters more than raw parameter count.
Which graphics cards have 24GB of VRAM?
Cards with 24GB include GeForce RTX 4090, GeForce RTX 3090, Radeon RX 7900 XTX.

Other VRAM amounts

4GB6GB8GB10GB12GB16GB32GB