neopolita/Qwen3.8-Flash-Next-113B-A5B-Niwaki-3bit-mlx

Partial fine-tune vs mlx-community/Qwen3.8-Flash-Next-4bit. Partial change: 5% of the weights changed (mlp), in 31 of 32 layers.

Tensors changed: Embeddings 0/6, Attention 0/836, Norms 0/121, MLP 279/744, other 0/7

1 derivatives checked

• neopolita/Qwen3.8-Flash-Next-113B-A5B-Niwaki-3bit-gguf: Quantization

On the Hub · Downloads on Model Pulse