For anyone wanting GGUFs, I uploaded them to https://huggingface.co/collections/unsloth/deepseek-r1-all-v...
There's the distilled R1 GGUFs for Llama 8B, Qwen 1.5B, 7B, 14B, and I'm still uploading Llama 70B and Qwen 32B.
Also I uploaded a 2bit quant for the large MoE (200GB in disk size) to https://huggingface.co/unsloth/DeepSeek-R1-GGUF
Thank you.
Which is currently the most capable version running reasonably fast on a 3090 (24GB of VRAM)?
loading story #42770790