magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF

Quantization (fewer layers) vs unsloth/Qwen3-VL-8B-Thinking. magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF matches part of unsloth/Qwen3-VL-8B-Thinking (399 of its 750 tensors; the rest of unsloth/Qwen3-VL-8B-Thinking has no counterpart). On the shared part: magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 254 within quantization error.

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

On the Hub · Downloads on Model Pulse