← Back to Models
MosaicMLtransformer
MPT 30B Chat
30B parameters • 18.3GB VRAM (Q4 estimate) • 8,192 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
30B
VRAM (Q4 est.)
18.3 GB
VRAM (FP16)
60 GB
Context Window
8,192
Architecture
transformer
License
Apache-2.0
Finding cloud alternatives...
Run MPT 30B Chat on RTX 4000 Ada
~18.3GB VRAM needed at Q4. RTX 4000 Ada has 20GB — 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 MPT 30B Chat
Compatibility Lab — check every GPU × quantization combination