Best local AI models for 4GB VRAM

Ranked by what actually fits at 32K context, computed from real file bytes.

A 4GB card gives you about 3.72 GiB to work with after driver overhead. 2 indexed models fit at 32K context — the largest being Wan2.2-TI2V-5B at 5.0B parameters in Q4_0.

From the file· fit from summed bytesFrom the file· KV per layer

Fits in 4GB at 32K context

largest quantization that fits, per model
ModelModalityBest quantParamsTotalHeadroom
Wan2.2-TI2V-5Bvideo generationQ4_05.0B3.66 GiB0.06 GiB
Wan2.2-TI2V-5B-Turbovideo generationQ4_05.0B3.66 GiB0.06 GiB
Spec sheetPredictedwhat these mean

This page models a generic 4GB accelerator, so it answers what fits rather than how fast it runs. For tokens per second you need a specific card — pick one from hardware, where bandwidth is known.