Mungert/Jan-v2-VL-high-GGUF
Partial fine-tune (fewer layers) vs Qwen/Qwen3-VL-8B-Thinking. Mungert/Jan-v2-VL-high-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: Mungert/Jan-v2-VL-high-GGUF is a GGUF (Q8_0) of different weights. Partial change: 85% of the weights changed (attention, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 91/145, MLP 108/108, Attention 144/144, lm_head 0/1