RedFT/Qwen3.8-Flash-Next-AWQ-W4A16-FP8PLE

Partial fine-tune vs wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16. Partial change: 90% of the weights changed (embeddings), in 1 of 48 layers.

Tensors changed: Embeddings 128/137, MLP 0/1943, Attention 0/608, Norms 0/302, other 0/8, lm_head 0/1

On the Hub · Downloads on Model Pulse