ubergarm/GigaChat3-10B-A1.8B-GGUF

Quantization vs ai-sage/GigaChat3-10B-A1.8B-bf16. ubergarm/GigaChat3-10B-A1.8B-GGUF is a GGUF quantization (Q8_0) of the same weights: 104 tensors match exactly and 158 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/79, MLP 0/103, Attention 0/78

On the Hub · Downloads on Model Pulse