zai-org/GLM-5.3
63 derivatives checked
- unsloth/GLM-5.3-GGUF: Quantization
- nvidia/GLM-5.3-NVFP4: Different architecture
- Justvugg/GLM-5.3-colibri-int4-g64: Quantization
- amd/GLM-5.3-Quark-MXFP4-AttnFP8: Different architecture
- incoai/GLM-5.3-DFlash2: Quantization
- autotrust/GLM-5.3-GGUF-DGX-Spark: Quantization
- incoai/GLM-5.3-NVFP4: Different architecture
- RedHatAI/GLM-5.3-MXFP4: Different architecture
- RedHatAI/GLM-5.3-NVFP4: Different architecture
- OneNexus/GLM-5.3-MXFP4: Different architecture
- orcarouter/GLM-5.3-MLX: Different architecture
- dealignai/GLM-5.3-UNCENSORED-NVFP4: Different architecture
- gpustack/GLM-5.3-W4A8: Different architecture
- Tech2wild/GLM-5.3-Int4-Int8Mix: Different architecture
- davidsyoung/GLM-5.3-EXL3-TR3-3.42bpw: Quantization
- dealignai/GLM-5.3-ABLITERATED-NVFP4: Different architecture
- jarrelscy/GLM-5.3-Vision-NestQuant-2-4bit: Same weights, repacked (fewer layers)
- drowzeys/keys-GLM-5.3-EXL3-2.75BPW: Quantization
- RedHatAI/GLM-5.3-speculator.dspark: Quantization
- inference-optimization/GLM-5.3-0.6B-A0.4B: Quantization
- local-inference-lab/GLM-5.3-NVFP4: Different architecture
- 0xSero/GLM-5.3-500B-EXL3-3.0bpw: Quantization
- pipenetwork/GLM-5.3-MLX-mixed-4_8bit: Different architecture
- DevQuasar/zai-org.GLM-5.3-GGUF: Quantization
- AlayaNeW/GLM-5.3-DSpark: Quantization
- unsloth/GLM-5.3: Quantization
- pipenetwork/GLM-5.3-MLX-4bit: Different architecture
- cyankiwi/GLM-5.3-AWQ-INT4: Different architecture
- vogel61/GLM-5.3-oQ4e: Different architecture
- 0xSero/GLM-5.3-EXL3-3.0bpw: Quantization
49 other repos hold byte-for-byte identical weight files.