Text model · DeepSeek-R1-Distill
DeepSeek-R1-Distill-Qwen 32B requirements
DeepSeek-R1-Distill family · 32B params · released Jan 2025 · 79.3M Ollama pulls. Minimum to run at Q4_K_M: Nvidia GeForce RTX 4090 (24GB).
Quantization sizes
| Quantization | Size on disk |
|---|---|
| Q2_K | 13.4 GB est |
| Q3_K_M | 15.6 GB est |
| Q4_K_M (default) | 19.85 GB |
| Q5_K_M | 22.8 GB est |
| Q6_K | 26.2 GB est |
| Q8_0 | 34.82 GB |
| FP16 | 64 GB est |
Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.
Run it
ollama run deepseek-r1:32b llama-cli -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M lms get bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF Which devices can run DeepSeek-R1-Distill-Qwen 32B?
Apple Silicon Macs
RAM-only laptops
iPhone & iPad
Android
NVIDIA GPUs
FAQ
How much VRAM or RAM does DeepSeek-R1-Distill-Qwen 32B need?
At Q4_K_M, DeepSeek-R1-Distill-Qwen 32B needs about 22.1 GB (weights ~19.85 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~37 GB.
Can DeepSeek-R1-Distill-Qwen 32B run on a laptop?
DeepSeek-R1-Distill-Qwen 32B is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.
Can I use DeepSeek-R1-Distill-Qwen 32B commercially?
Yes. DeepSeek-R1-Distill-Qwen 32B is licensed MIT, which permits commercial use.
Distilled from DeepSeek-R1 onto Qwen2.5-32B base. Released 2025-01-20. Q4_K_M=19.85GB, Q8_0=34.82GB from bartowski HF repo. Ollama shows 20GB. Context 128K.
Sources
Memory figures are estimates. See methodology.