zai-org/GLM-5.2
65 derivatives checked
- nvidia/GLM-5.2-NVFP4: Quantization
- unsloth/GLM-5.2-GGUF: Same weights, converted
- amd/GLM-5.2-MXFP4: Quantization
- brandonmusic/GLM-5.2-EXL3-TR3v4-3.5bpw-MTP78: Different architecture
- malaiwah/GLM-5.2-EXL3-FQ-segments: Different architecture
- mastouri/GLM-5.2-colibri-int4-g64-with-int8-mtp: Different architecture
- inference-optimization/GLM-5.2-0.8B-A0.8B: Different architecture
- tiny-random/glm-5.2: Different architecture
- huihui-ai/Huihui-GLM-5.2-abliterated-GGUF: Full fine-tune
- RedHatAI/GLM-5.2-NVFP4-FP8: Quantization
- QuantTrio/GLM-5.2-Int4-Int8Mix: Quantization
- philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX: Quantization
- local-inference-lab/GLM-5.2-NVFP4: Quantization
- mlx-community/GLM-5.2-DQ4plus-q8: Quantization
- DevQuasar/zai-org.GLM-5.2-GGUF: Quantization
- mastouri/GLM-5.2-colibri-E8-IQ3-with-int8-mtp: Different architecture
- mlx-community/GLM-5.2-4bit: Quantization
- cyankiwi/GLM-5.2-AWQ-INT4: Quantization
- RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK: Quantization
- canada-quant/GLM-5.2-W4A16-MTP: Quantization
- yujiepan/glm-5.2-tiny-random: Different architecture
- inferencerlabs/GLM-5.2-MTP-MLX: Quantization
- turintech/GLM-5.2-MaxMin108-GGUF: Quantization
- pipenetwork/GLM-5.2-MLX-mixed-3_6bit: Quantization
- sunshaohui/GLM-5.2-GGUF: Same weights, converted
- baseten/GLM-5.2-Vision-NVFP4: Quantization
- vinayakkamboj/compressed-backup-GLM-5.2-GGUF: Same weights, converted
- pipenetwork/GLM-5.2-REAP50-MLX-4bit: Quantization
- 0xSero/GLM-5.2-504B: Quantization
- 0xSero/GLM-5.2-REAP-504B-GGUF: Same weights, converted
119 other repos hold byte-for-byte identical weight files.