Clef-Flash decision model in GGUF, compressed by TurinTech with Artemis. Use the /v1/systemone endpoint, not chat. Recommended: Clef-Flash-Artemis-IQ4_XS.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/Clef-Flash-Artemis-GGUF. Download size is not runtime memory. Measured IQ4_XS: same answer as BF16 95.0%, 0 confident answers changed on typed-decisions test split (all 400 cases); protocol cpu-ryzen9950x-20261011.

Clef-Flash decision model in GGUF, compressed by TurinTech with Artemis. Use the /v1/systemone endpoint, not chat. Recommended: Clef-Flash-Artemis-IQ4_XS.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/Clef-Flash-Artemis-GGUF. Download size is not runtime memory. Measured IQ4_XS: same answer as BF16 95.0%, 0 confident answers changed on typed-decisions test split (all 400 cases); protocol cpu-ryzen9950x-20261011.