bobchenyx/DeepSeek-R1-0528-HFK-GGUF

Llamacpp Quantizations of DeepSeek-R1-0528 (MLA version)

Original model: Adopting BF16 & Imatrix from unsloth/DeepSeek-R1-0528-GGUF.

• Expert 2-bit : 210.78 GiB (2.70 BPW)

• Expert 2-bit(XL) : 215.90 GiB (2.76 BPW)

Download Guide

# !pip install huggingface_hub hf_transfer
import os
os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
from huggingface_hub import snapshot_download
snapshot_download(
    repo_id = "bobchenyx/DeepSeek-R1-0528-HFK-GGUF",
    local_dir = "bobchenyx/DeepSeek-R1-0528-HFK-GGUF",
    allow_patterns = ["*Q2_K*"],
)