IQ2_KS quant from lmganon123
See here for an IQ2_KS quant from lmganon123:
lmganon123/DeepSeek-R1_IK_GGUF_Q2
Due to new storage limits introduced by HuggingFace, the GGUF files (30 × 46GB = ~1.38TB) have been moved to ModelScope.
1from modelscope import snapshot_download
2model_dir = snapshot_download('quantzor/DeepSeek-R1-OG-256x21B-BF16')