mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF

Quantization vs DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2. mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF is a GGUF quantization (Q8_0) of the same weights: 111 tensors match exactly and 87 within quantization error.

Tensors changed: Embeddings 0/2, other 0/48, MLP 0/36, Norms 0/80, Attention 0/32

On the Hub · Downloads on Model Pulse