GLM-5.2-FP8-Uncensored BF16

llama-cli -hf phaseonx11/GLM-5.2-Uncensored-GGUF:BF16

Downloads and runs in one step, resolving the quantization by name.

hf download phaseonx11/GLM-5.2-Uncensored-GGUF --include "glm52-BF16-00001-of-00038.gguf"

This quantization is split across 38 files totalling 1403.43 GiB. You need every part — the first is not a smaller version of the model.

• glm52-BF16-00001-of-00038.gguf
• glm52-BF16-00002-of-00038.gguf
• glm52-BF16-00003-of-00038.gguf
• glm52-BF16-00004-of-00038.gguf
• glm52-BF16-00005-of-00038.gguf
• glm52-BF16-00006-of-00038.gguf
• glm52-BF16-00007-of-00038.gguf
• glm52-BF16-00008-of-00038.gguf
• glm52-BF16-00009-of-00038.gguf
• glm52-BF16-00010-of-00038.gguf
• glm52-BF16-00011-of-00038.gguf
• glm52-BF16-00012-of-00038.gguf
• glm52-BF16-00013-of-00038.gguf
• glm52-BF16-00014-of-00038.gguf
• glm52-BF16-00015-of-00038.gguf
• glm52-BF16-00016-of-00038.gguf
• glm52-BF16-00017-of-00038.gguf
• glm52-BF16-00018-of-00038.gguf
• glm52-BF16-00019-of-00038.gguf
• glm52-BF16-00020-of-00038.gguf
• glm52-BF16-00021-of-00038.gguf
• glm52-BF16-00022-of-00038.gguf
• glm52-BF16-00023-of-00038.gguf
• glm52-BF16-00024-of-00038.gguf
• glm52-BF16-00025-of-00038.gguf
• glm52-BF16-00026-of-00038.gguf
• glm52-BF16-00027-of-00038.gguf
• glm52-BF16-00028-of-00038.gguf
• glm52-BF16-00029-of-00038.gguf
• glm52-BF16-00030-of-00038.gguf
• glm52-BF16-00031-of-00038.gguf
• glm52-BF16-00032-of-00038.gguf
• glm52-BF16-00033-of-00038.gguf
• glm52-BF16-00034-of-00038.gguf
• glm52-BF16-00035-of-00038.gguf
• glm52-BF16-00036-of-00038.gguf
• glm52-BF16-00037-of-00038.gguf
• glm52-BF16-00038-of-00038.gguf

Straight from the Hugging Face CDN — we host nothing and earn nothing from this. Verify what you received against the exact byte count above; a size mismatch is the usual cause of a file that will not load.