Best local AI models for 20GB VRAM
Ranked by what actually fits at 32K context, computed from real file bytes.
A 20GB card gives you about 18.60 GiB to work with after driver overhead. 2 indexed models fit at 32K context — the largest being HunyuanImage-2.1 at 17.5B parameters in IQ3_S.
From the file· fit from summed bytesFrom the file· KV per layer
Fits in 20GB at 32K context
largest quantization that fits, per model
| Model | Modality | Best quant | Params○ | Total◐ | Headroom◐ |
|---|---|---|---|---|---|
| HunyuanImage-2.1 | image generation | IQ3_S | 17.5B | 17.36 GiB | 1.24 GiB |
| Janus-Pro-7B | image generation | I1-IQ3_XXS | 7.4B | 18.40 GiB | 0.20 GiB |
This page models a generic 20GB 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.