Skip to content

AI Model Finder

Filter open-weight models by type, parameter size and license — and see how much VRAM each one needs.

4 of 4 models, sorted by rating

Llama 3.1 8B Instruct

The default local workhorse: fast, permissive license, great 8B quality — fits in 8 GB of VRAM at Q4.

llm8B paramsMeta Llama 3.1 Community Licensemin 8 GB (Q4) VRAM★ 4.5

Stable Diffusion XL

The reference open image model for local generation: 12 GB VRAM recommended, huge ecosystem of LoRAs and workflows.

imageCreativeML Open RAIL++-Mmin 8 GB VRAM★ 4.5

Gemma 3 12B

Google’s mid-size open model: strong multilinguality and multimodality in a package that fits a 16 GB GPU.

llm12B paramsGemma Terms of Usemin 12 GB (Q4) VRAM★ 4.4

Mistral 7B Instruct v3

Apache-licensed, 128k context, excellent multilingual quality — a strong open alternative to Llama 8B.

llm7.3B paramsApache 2.0min 8 GB (Q4) VRAM★ 4.3