inference-optimization/Qwen3.8-1.0B-A0.6B

Different architecture vs Qwen/Qwen3.8-2.4T-A95B. Different architecture: only 0 of 1609/141 tensors match by name and shape.

1 derivatives checked

• TEKIBO/Qwen3.8-1.0B-A0.6B-Q4_0-GGUF: Quantization

On the Hub · Downloads on Model Pulse