TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill
LoRA-style vs unsloth/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, o_proj, up_proj changed, in 47 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/196, MLP 141/2559, Attention 47/240, lm_head 0/1, other 0/2
13 derivatives checked
- TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF: Same weights, converted
- titantv090/GLM-4.7-Flash-Claude-Opus-4.6-High-Reasoning-Distill-GGUF: Same weights, converted
- rounakchhatait/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF: Same weights, converted
- zsjTiger/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF: Same weights, converted
- mrbrz/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF: Same weights, converted
- aiworksofbt/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF: Same weights, converted
- witflag/Synex: Same weights, converted
- Joshua-Xia/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF: Same weights, converted
- noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill: Quantization
- mlx-community/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-4bit: Quantization
- PaulZaff/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF: Same weights, converted
- mlx-community/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-6bit: Quantization
- mlx-community/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-8bit: Quantization