← Back to Models
DeepSeektransformer
DeepSeek Coder 33B
33B parameters • 20.1GB VRAM (Q4 estimate) • 16,384 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
33B
VRAM (Q4 est.)
20.1 GB
VRAM (FP16)
66 GB
Context Window
16,384
Architecture
transformer
License
Apache-2.0
Finding cloud alternatives...
Run DeepSeek Coder 33B on Mac Mini M4 Pro 24GB
~20.1GB VRAM needed at Q4. Mac Mini M4 Pro 24GB has 24GB — 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 33B
Compatibility Lab — check every GPU × quantization combination