mradermacher/Ektome-Qwen3-VL-2Bi-PristinelyUncensored-GGUF

Same weights, converted (fewer layers) vs Zynerji/Ektome-Qwen3-VL-2Bi-PristinelyUncensored. mradermacher/Ektome-Qwen3-VL-2Bi-PristinelyUncensored-GGUF matches part of Zynerji/Ektome-Qwen3-VL-2Bi-PristinelyUncensored (310 of its 625 tensors; the rest of Zynerji/Ektome-Qwen3-VL-2Bi-PristinelyUncensored has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse