mradermacher/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF

Same weights, converted (fewer layers) vs prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX. mradermacher/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF matches part of prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX (399 of its 750 tensors; the rest of prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX 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