bartowski/OpenGVLab_InternVL3_5-38B-GGUF

Same weights, converted (fewer layers) vs OpenGVLab/InternVL3_5-38B. bartowski/OpenGVLab_InternVL3_5-38B-GGUF matches part of OpenGVLab/InternVL3_5-38B (707 of its 1302 tensors; the rest of OpenGVLab/InternVL3_5-38B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: Attention 0/256, Norms 0/257, MLP 0/192, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse