llmfan46/Qwen3-VL-32B-Instruct-ultra-uncensored-heretic-GGUF

Same weights, converted (fewer layers) vs llmfan46/Qwen3-VL-32B-Instruct-ultra-uncensored-heretic. llmfan46/Qwen3-VL-32B-Instruct-ultra-uncensored-heretic-GGUF matches part of llmfan46/Qwen3-VL-32B-Instruct-ultra-uncensored-heretic (707 of its 1058 tensors; the rest of llmfan46/Qwen3-VL-32B-Instruct-ultra-uncensored-heretic has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

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

On the Hub · Downloads on Model Pulse