Kev 9B decision model in GGUF, compressed by TurinTech with Artemis. Use the /v1/systemone endpoint, not chat. Recommended: Kev-9B-Artemis-IQ3_M.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/Kev-9B-Artemis-GGUF. Download size is not runtime memory. Measured IQ3_M: same answer as BF16 92.2%, 0 confident answers changed on typed-decisions test split (selection panel); protocol kev9b-a100-20261012.
Kev 9B decision model in GGUF, compressed by TurinTech with Artemis. Use the /v1/systemone endpoint, not chat. Recommended: Kev-9B-Artemis-IQ3_M.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/Kev-9B-Artemis-GGUF. Download size is not runtime memory. Measured IQ3_M: same answer as BF16 92.2%, 0 confident answers changed on typed-decisions test split (selection panel); protocol kev9b-a100-20261012.
Kev 9B decision model in GGUF, compressed by TurinTech with Artemis. Use the /v1/systemone endpoint, not chat. Recommended: Kev-9B-Artemis-IQ3_M.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/Kev-9B-Artemis-GGUF. Download size is not runtime memory. Measured IQ3_M: same answer as BF16 92.2%, 0 confident answers changed on typed-decisions test split (selection panel); protocol kev9b-a100-20261012.
Kev 9B decision model in GGUF, compressed by TurinTech with Artemis. Use the /v1/systemone endpoint, not chat. Recommended: Kev-9B-Artemis-IQ3_M.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/Kev-9B-Artemis-GGUF. Download size is not runtime memory. Measured IQ3_M: same answer as BF16 92.2%, 0 confident answers changed on typed-decisions test split (selection panel); protocol kev9b-a100-20261012.