← Back to Models
DeepSeektransformer
DeepSeek R1 Distill Qwen 32B
32B parameters • 19.5GB 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
32B
VRAM (Q4 est.)
19.5 GB
VRAM (FP16)
64 GB
Context Window
128,000
Architecture
transformer
License
MIT
Finding cloud alternatives...
Run DeepSeek R1 Distill Qwen 32B on RTX 4000 Ada
~19.5GB 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 DeepSeek R1 Distill Qwen 32B
Compatibility Lab — check every GPU × quantization combination