Mungert/MiMo-VL-7B-RL-GGUF

Quantization (fewer layers) vs XiaomiMiMo/MiMo-VL-7B-RL. Mungert/MiMo-VL-7B-RL-GGUF matches part of XiaomiMiMo/MiMo-VL-7B-RL (435 of its 825 tensors; the rest of XiaomiMiMo/MiMo-VL-7B-RL has no counterpart). On the shared part: Mungert/MiMo-VL-7B-RL-GGUF is a GGUF quantization (Q8_0) of the same weights: 291 tensors match exactly and 144 within quantization error.

Tensors changed: Norms 0/73, MLP 0/108, Attention 0/252, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse