Anbeeld/Qwen3.8-27B-DFlash2-GGUF

Same weights, converted vs incoai/Qwen3.8-27B-DFlash2. Same weights stored in another dtype (BF16 → BF16/F32), plus 24 new tensors.

Tensors changed: other 0/1, Norms 0/21, MLP 0/15, Attention 0/20

1 derivatives checked

• Blazestorm001/Qwen3.8-27B-ASCII-Condensed-DFlash2-GGUF: Quantization

On the Hub · Downloads on Model Pulse