CanMyPCRunAILocal AI compatibility
Check my PC

What AI models can you run with 16GB of VRAM?

With 16GB of VRAM, 170 of 228 models from the Ollama library run entirely on the GPU at 4K context. 34 more run by offloading part of the model to system RAM, which works but is slower.

170

run well

34

with trade-offs

228

models tested

Check my actual PC

Best AI models for 16GB of VRAM

Heaviest first — each of these fits entirely in 16GB at 4K context, counting weights, KV cache, compute buffers and runtime overhead.

Models that fit in 16GB of VRAM
ModelBuildMemory neededVerdict
deepseek-coder-v216B~14.2 GBGood fit
deepseek-v216B~14.2 GBGood fit
phi414B~12.4 GBGood 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
deepseek-ocr3B~9.3 GBExcellent fit
nous-hermes210.7B~9.0 GBExcellent fit
solar10.7B~9.0 GBExcellent fit
codegeex49B~8.7 GBExcellent fit
glm49B~8.7 GBExcellent fit
ornith-1.59B~7.9 GBExcellent fit
ornith9B~7.9 GBExcellent fit
gemma3ne2b-it-q4_K_M~7.9 GBExcellent fit
lfm2.58B~7.3 GBExcellent fit
granite4.1-guardian8B~7.2 GBExcellent fit
rnj-18B~7.2 GBExcellent fit
command-r7b-arabic7B~7.1 GBExcellent fit

Graphics cards with 16GB of VRAM

GeForce RTX 5080GeForce RTX 5070 TiGeForce RTX 5060 Ti 16GBGeForce RTX 4080GeForce RTX 4060 Ti 16GBRadeon RX 9070 XTRadeon RX 9060 XT 16GBRadeon RX 7800 XTRadeon RX 6800 XT

How this was calculated

Every model is evaluated at 4K context against 16GB 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.

16GB VRAM and local AI — frequently asked questions

Is 16GB of VRAM enough to run AI models locally?
Yes — 170 of the 228 models tested run entirely on the GPU with 16GB at 4K context, and 34 more run with part of the model offloaded to system RAM. The heaviest that fits is deepseek-coder-v2:16b-lite-base-q4_K_M, needing about 14.2 GB.
What is the best AI model for 16GB VRAM?
For maximum capability, deepseek-coder-v2 (deepseek-coder-v2:16b-lite-base-q4_K_M) is the heaviest build that still fits entirely in 16GB. Smaller models leave headroom for a longer context window, which often matters more than raw parameter count.
Which graphics cards have 16GB of VRAM?
Cards with 16GB include GeForce RTX 5080, GeForce RTX 5070 Ti, GeForce RTX 5060 Ti 16GB, GeForce RTX 4080, GeForce RTX 4060 Ti 16GB, Radeon RX 9070 XT, Radeon RX 9060 XT 16GB, Radeon RX 7800 XT, Radeon RX 6800 XT.

Other VRAM amounts

4GB6GB8GB10GB12GB24GB32GB