cerebras/GLM-4.7-Flash-REAP-23B-A3B
LoRA-style vs zai-org/GLM-4.7-Flash. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, up_proj changed, in 46 of 47 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/189, MLP 1630/1822, Attention 0/235, lm_head 0/1
9 derivatives checked
- unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF: Same weights, converted
- mradermacher/GLM-4.7-Flash-REAP-23B-A3B-i1-GGUF: Quantization
- mradermacher/GLM-4.7-Flash-REAP-23B-A3B-GGUF: Quantization
- cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-4bit: Quantization
- cafepm/GLM-4.7-Flash-REAP-23B-A3B-Q3Q4-GGUF: Quantization
- noctrex/GLM-4.7-Flash-REAP-23B-A3B-MXFP4_MOE-GGUF: Quantization
- RepublicOfKorokke/GLM-4.7-Flash-REAP-23B-A3B-mlx-nvfp4: Quantization
- RepublicOfKorokke/GLM-4.7-Flash-REAP-23B-A3B-oQ4: Quantization
- MuXodious/GLM-4.7-Flash-REAP-23B-A3B-absolute-heresy: Abliterated
1 other repos hold byte-for-byte identical weight files.