OpenMOSE/Qwen3-VL-REAP-145B-A22B

Same weights, repacked vs Qwen/Qwen3-VL-235B-A22B-Instruct. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/4, Norms 0/493, Attention 0/484, MLP 0/124, lm_head 0/1

1 derivatives checked

• mradermacher/Qwen3-VL-REAP-145B-A22B-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse