← Back to Models
Metatransformer
Llama 3.2 90B Vision
90B parameters • 49.5GB VRAM (Q4) • 128,000 context
Specifications
Parameters
90B
VRAM (Q4)
49.5 GB
VRAM (FP16)
180 GB
Context Window
128,000
Architecture
transformer
License
Apache-2.0
Finding cloud alternatives...
Run Llama 3.2 90B Vision on NVIDIA A16
~49.5GB VRAM needed at Q4. NVIDIA A16 has 64GB — buy hardware or rent cloud.
We may earn a commission from cloud and hardware partners at no extra cost to you.
Find the cheapest GPU that can run Llama 3.2 90B Vision
Compatibility Lab — check every GPU × quantization combination