unsloth/InternVL3-78B-Instruct-GGUF

Same weights, converted (fewer layers) vs OpenGVLab/InternVL3-78B-Instruct. unsloth/InternVL3-78B-Instruct-GGUF matches part of OpenGVLab/InternVL3-78B-Instruct (963 of its 1558 tensors; the rest of OpenGVLab/InternVL3-78B-Instruct has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: Embeddings 0/1, MLP 0/240, Attention 0/560, Norms 0/161, lm_head 0/1

On the Hub · Downloads on Model Pulse