mradermacher/AgentMercury-Qwen3.5-35B-A3B-SAO-GGUF

Quantization vs Minbyul/AgentMercury-Qwen3.5-35B-A3B-SAO. mradermacher/AgentMercury-Qwen3.5-35B-A3B-SAO-GGUF is a GGUF quantization (Q8_0) of the same weights: 141 tensors match exactly and 162 within quantization error.

Tensors changed: Norms 0/101, MLP 0/160, Attention 0/40, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse