ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF

Same weights, converted vs moonshotai/Kimi-VL-A3B-Thinking-2506. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 158 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/82, MLP 0/107, Attention 0/81, lm_head 0/1

On the Hub · Downloads on Model Pulse