can it run
No. 8GB of memory can't hold the 25GB working set this model needs. A smaller quant or a bigger machine is required.
| model file | 20GB (GGUF Q4_K_M) |
| minimum memory | 25GB working set |
| this machine | 8GB GDDR6, 448 GB/s |
| params | distill 32B |
| license | mit |
| price | $275 |
easy run: ollama pull deepseek-r1:32b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Mac mini M5 Pro (64GB) — cheapest machine that runs it ($1669)
→ every model the RTX 3070 (used) can run — full list