mradermacher/Qwen3-VL-8B-Instruct-GGUF

Same weights, converted (fewer layers) vs Qwen/Qwen3-VL-8B-Instruct. mradermacher/Qwen3-VL-8B-Instruct-GGUF matches part of Qwen/Qwen3-VL-8B-Instruct (399 of its 750 tensors; the rest of Qwen/Qwen3-VL-8B-Instruct has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1

On the Hub · Downloads on Model Pulse