← Back to Models
Metatransformer
Llama 3.3 70B Instruct
70B parameters • 42.6GB VRAM (Q4 estimate) • 128,000 context
Estimate · Q4_K_M · 4k context · batch 1. For dense 7B–70B this sits ~5–8% above the Q4_K_M GGUF file. Not peak runtime VRAM and not a measured bench.
Specifications
Parameters
70B
VRAM (Q4 est.)
42.6 GB
VRAM (FP16)
140 GB
Context Window
128,000
Architecture
transformer
License
Llama 3.3 Community License
Finding cloud alternatives...
Run Llama 3.3 70B Instruct on Mac Mini M4 Pro 48GB
~42.6GB VRAM needed at Q4. Mac Mini M4 Pro 48GB has 48GB — 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 3.3 70B Instruct
Compatibility Lab — check every GPU × quantization combination