← Back to Models
Mistral AItransformer
Mistral Large (API)
123B parameters • 74.9GB 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
123B
VRAM (Q4 est.)
74.9 GB
VRAM (FP16)
246 GB
Context Window
128,000
Architecture
transformer
License
Mistral API TOS
Finding cloud alternatives...
Run Mistral Large (API) on A100 SXM4 80 GB
~74.9GB VRAM needed at Q4. A100 SXM4 80 GB has 80GB — 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 Mistral Large (API)
Compatibility Lab — check every GPU × quantization combination