redponike/Qwen3-VL-2B-Thinking-GGUF

Quantization (fewer layers) vs Qwen/Qwen3-VL-2B-Thinking. redponike/Qwen3-VL-2B-Thinking-GGUF matches part of Qwen/Qwen3-VL-2B-Thinking (310 of its 625 tensors; the rest of Qwen/Qwen3-VL-2B-Thinking has no counterpart). On the shared part: redponike/Qwen3-VL-2B-Thinking-GGUF is a GGUF quantization (Q8_0) of the same weights: 113 tensors match exactly and 197 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse