lmstudio-community/Qwen3-VL-8B-Thinking-GGUF

Quantization (fewer layers) vs Qwen/Qwen3-VL-8B-Thinking. lmstudio-community/Qwen3-VL-8B-Thinking-GGUF matches part of Qwen/Qwen3-VL-8B-Thinking (399 of its 750 tensors; the rest of Qwen/Qwen3-VL-8B-Thinking has no counterpart). On the shared part: lmstudio-community/Qwen3-VL-8B-Thinking-GGUF is a GGUF quantization (Q8_0) 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