DevQuasar/Qwen.Qwen3.8-2.4T-A95B-GGUF

Quantization vs Qwen/Qwen3.8-2.4T-A95B. DevQuasar/Qwen.Qwen3.8-2.4T-A95B-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 323 tensors match exactly and 370 within quantization error.

Tensors changed: Norms 0/231, MLP 0/368, Attention 0/92, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse