AI is happening. The future is updating.GLM-5.3-Flash-colibri-int4-g64
An int4 group-scaled conversion of `zai-org/GLM-5.3-Flash`, packed in the container format that colibrì streams from disk. **This is not the official checkpoint.** The weights are Z.ai's; this repository only changes how they are stored. It will not load in transformers or vLLM. It loads in colibrì's `glm53` engine and nothing else. Running a 321B multimodal model on a machine with 25 GB of RAM, by keeping the routed experts on disk and reading only the ones each token selects.
An int4 group-scaled conversion of `zai-org/GLM-5.3-Flash`, packed in the container format that colibrì streams from disk. **This is not the official checkpoint.** The weights are Z.ai's; this repository only changes how they are stored. It will not load in transformers or vLLM. It loads in colibrì's `glm53` engine and nothing else. Running a 321B multimodal model on a machine with 25 GB of RAM, by keeping the routed experts on disk and reading only the ones each token selects.