OpenMOSE/Qwen3-VL-REAP-24B-A3B

Same weights, repacked vs Qwen/Qwen3-VL-30B-A3B-Instruct. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/4, Norms 0/309, Attention 0/300, lm_head 0/1, MLP 0/124

2 derivatives checked

• mradermacher/Qwen3-VL-REAP-24B-A3B-GGUF: Quantization
• OpenMOSE/Qwen3-VL-REAP-24B-A3B-GGUF: Quantization

On the Hub · Downloads on Model Pulse