Best models for 12 GB VRAM

RTX 3060 12 GB / RTX 4070 / M-series Mac with 24 GB

12 GB unlocks bigger 12–14B models with a comfortable context window. Strong sweet spot for code, vision, and reasoning.

  1. 1

    Microsoft

    Phi-4

    Microsoft's 14B parameter model. Punches well above its weight on reasoning.

    14B≥ 8.93 GB
  2. 2

    Alibaba

    Qwen 2.5 14B

    Strong 14B model with excellent coding and reasoning. iPad Pro recommended.

    14B≥ 8.87 GB
  3. 3

    Alibaba

    Qwen 2.5 Coder 14B

    Powerful 14B code model. Excellent for complex programming tasks.

    14B≥ 8.87 GB
  4. 4

    Google

    Gemma 3 12B

    High quality 12B model. Excellent for iPad Pro and Mac.

    12B≥ 7.3 GB
  5. 5

    Mistral AI

    Mistral Nemo 12B

    Mistral's 12B model with excellent instruction following.

    12B≥ 7.46 GB
  6. 6

    Microsoft

    Phi-3.5 Vision

    Vision-language model from Microsoft. Can understand images and documents.

    4.2B≥ 3.2 GB
  7. 7

    LLaVA

    LLaVA 1.6 7B

    Multimodal vision-language model. Understands images and answers questions about them.

    7B≥ 5 GB
  8. 8

    Black Forest Labs

    FLUX.1 Schnell (GGUF)

    Fast 1-4 step generation. State-of-the-art quality. Needs 16GB+ RAM.

    12B≥ 14 GB

Not sure which fits your machine? Auto-detect your hardware →