mradermacher/Qwen-SEA-LION-v4-8B-VL-GGUF
Same weights, converted (fewer layers) vs aisingapore/Qwen-SEA-LION-v4-8B-VL. mradermacher/Qwen-SEA-LION-v4-8B-VL-GGUF matches part of aisingapore/Qwen-SEA-LION-v4-8B-VL (399 of its 750 tensors; the rest of aisingapore/Qwen-SEA-LION-v4-8B-VL has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1