GeoMaciolek/Qwen3.8-32B-Jumbo-Q4_K_S-GGUF

Quantization vs StargazerLabs/Qwen3.8-32B-Jumbo. GeoMaciolek/Qwen3.8-32B-Jumbo-Q4_K_S-GGUF is a GGUF quantization (Q4_K_S) of the same weights: 191 tensors match exactly and 306 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/191, MLP 0/228, Attention 0/76

On the Hub · Downloads on Model Pulse