mradermacher/MiMo-VL-7B-RL-2508-GGUF

Same weights, converted (fewer layers) vs XiaomiMiMo/MiMo-VL-7B-RL-2508. mradermacher/MiMo-VL-7B-RL-2508-GGUF matches part of XiaomiMiMo/MiMo-VL-7B-RL-2508 (435 of its 825 tensors; the rest of XiaomiMiMo/MiMo-VL-7B-RL-2508 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse