mradermacher/Qwen3-VL-2B-Ties-Mix-GGUF

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

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

On the Hub · Downloads on Model Pulse