Userb1az/Kimi-VL-A3B-Thinking-2506-GGUF
Full fine-tune vs moonshotai/Kimi-VL-A3B-Instruct. Userb1az/Kimi-VL-A3B-Thinking-2506-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 27 of 27 layers.
Tensors changed: Embeddings 1/1, Norms 82/82, MLP 107/107, Attention 81/81, lm_head 1/1