mradermacher/Qwen-3-VL-2B-Instruct-heretic-GGUF

Same weights, converted (fewer layers) vs heretic-org/Qwen-3-VL-2B-Instruct-heretic. mradermacher/Qwen-3-VL-2B-Instruct-heretic-GGUF matches part of heretic-org/Qwen-3-VL-2B-Instruct-heretic (310 of its 625 tensors; the rest of heretic-org/Qwen-3-VL-2B-Instruct-heretic 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