John1604/Qwen3-VL-4B-Thinking-gguf

Quantization (fewer layers) vs Qwen/Qwen3-VL-4B-Thinking. John1604/Qwen3-VL-4B-Thinking-gguf matches part of Qwen/Qwen3-VL-4B-Thinking (398 of its 713 tensors; the rest of Qwen/Qwen3-VL-4B-Thinking has no counterpart). On the shared part: John1604/Qwen3-VL-4B-Thinking-gguf is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 253 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144

On the Hub · Downloads on Model Pulse