This model was converted and quantized using the official tools provided by llama.cpp.

Serving:

./build/bin/llama-server --mmproj /models/mmproj-MiMo-VL-7B-RL-f16.gguf \
    -m /models/MiMo-VL-7B-RL-q4_k_m.gguf -ngl 999

./build/bin/llama-server --mmproj /models/mmproj-MiMo-VL-7B-RL-q8_0.gguf \
    -m /models/MiMo-VL-7B-RL-q4_k_m.gguf -ngl 999

Downloads last month: 38

GGUF

Model size

8B params

Architecture

qwen2vl

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for yeahdongcn/MiMo-VL-7B-RL-q4_k_m-gguf

Unable to build the model tree, the base model loops to the model itself. Learn more.