Official Microsoft BitNet W2A8 / w1.58a8 packed checkpoint (model_state_int2.pt). Produced with gpu/convert_safetensors.py + gpu/convert_checkpoint.py on gpu5080 CPU (vLLM left resident). Not GGUF Q4.

Further strategic intelligent quant from this pack is later.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

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