DevQuasar/Qwen.Qwen3-VL-235B-A22B-Instruct-GGUF

Same weights, converted vs Qwen/Qwen3-VL-235B-A22B-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 282 new tensors.

Tensors changed: Embeddings 0/1, MLP 0/94, Norms 0/377, Attention 0/376, lm_head 0/1

On the Hub · Downloads on Model Pulse