← Back to Models
AI21 Labsmamba-transformer
Jamba 1.5 Large
398B parameters • 242.2GB VRAM (Q4 estimate) • 256,000 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
398B
VRAM (Q4 est.)
242.2 GB
VRAM (FP16)
796 GB
Context Window
256,000
Architecture
mamba-transformer
License
Jamba License
Finding cloud alternatives...
Run Jamba 1.5 Large on Mac Studio M3 Ultra 256GB
~242.2GB VRAM needed at Q4. Mac Studio M3 Ultra 256GB has 256GB — 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 Jamba 1.5 Large
Compatibility Lab — check every GPU × quantization combination