← Back to Models
DeepSeekmoe
DeepSeek Coder V2 16B
16B total / 2.4B active · load estimate uses total • 9.7GB 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
16B total / 2.4B active · load estimate uses total
VRAM (Q4 est.)
9.7 GB
VRAM (FP16)
32 GB
Context Window
128,000
Architecture
moe
License
Apache-2.0
Finding cloud alternatives...
Run DeepSeek Coder V2 16B on RTX 3080
~9.7GB VRAM needed at Q4. RTX 3080 has 10GB — 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 16B
Compatibility Lab — check every GPU × quantization combination