redponike/Qwen3-VL-32B-Thinking-GGUF

Quantization (fewer layers) vs Qwen/Qwen3-VL-32B-Thinking. redponike/Qwen3-VL-32B-Thinking-GGUF matches part of Qwen/Qwen3-VL-32B-Thinking (707 of its 1058 tensors; the rest of Qwen/Qwen3-VL-32B-Thinking has no counterpart). On the shared part: redponike/Qwen3-VL-32B-Thinking-GGUF is a GGUF quantization (Q8_0) of the same weights: 257 tensors match exactly and 450 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/257, MLP 0/192, Attention 0/256, lm_head 0/1

On the Hub · Downloads on Model Pulse