Best local AI models for 8GB VRAM

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

A 8GB card gives you about 7.44 GiB to work with after driver overhead. 1 indexed models fit at 32K context — the largest being HunyuanImage-2.1 at 17.5B parameters in Q2_K_S.

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

4GB 6GB 8GB 10GB 12GB 16GB 20GB 24GB 32GB 48GB 64GB 96GB 128GB

all image generation 1

Fits in 8GB at 32K context

largest quantization that fits, per model

Model	Modality	Best quant	Params○	Total◐	Headroom◐
HunyuanImage-2.1	image generation	Q2_K_S	17.5B	6.91 GiB	0.53 GiB

○Spec sheet◐Predictedwhat these mean

This page models a generic 8GB 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.