← Back to Models
DeepSeekmoe
DeepSeek Coder V2 236B
236B total / 21B active · load estimate uses total • 143.6GB 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
236B total / 21B active · load estimate uses total
VRAM (Q4 est.)
143.6 GB
VRAM (FP16)
472 GB
Context Window
128,000
Architecture
moe
License
DeepSeek License
Finding cloud alternatives...
Run DeepSeek Coder V2 236B on B300
~143.6GB VRAM needed at Q4. B300 has 144GB — 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 DeepSeek Coder V2 236B
Compatibility Lab — check every GPU × quantization combination