Full-precision safetensors of the wyrdsekai drive model, v6 — the source the deployment conversions come from: GGUF Q4_K_M for llama.cpp, MLX 4-bit for Apple Silicon. Published for re-quantization, further fine-tuning, and full-precision evaluation. Provenance: this checkpoint was verified by hash chain against the shipped GGUF's build directory.

See the GGUF card for lineage (v5 + emit-RFT), intended use and limitations. Training data: synthetic corpora only — the SFT line's data is published at wyrdsekai/drive-sft-corpus.