d3-mini decision model in GGUF, compressed by TurinTech with Artemis. Use the /v1/systemone endpoint, not chat. Recommended: d3-mini-Artemis-Q5_K_S.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/d3-mini-Artemis-GGUF. Download size is not runtime memory. Measured Q5_K_S: same answer as BF16 97.25%, 0 confident answers changed on the 160-case final set; protocol a100-620d222-20261025.
d3-mini decision model in GGUF, compressed by TurinTech with Artemis. Use the /v1/systemone endpoint, not chat. Recommended: d3-mini-Artemis-Q5_K_S.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/d3-mini-Artemis-GGUF. Download size is not runtime memory. Measured Q5_K_S: same answer as BF16 97.25%, 0 confident answers changed on the 160-case final set; protocol a100-620d222-20261025.
d3-mini decision model in GGUF, compressed by TurinTech with Artemis. Use the /v1/systemone endpoint, not chat. Recommended: d3-mini-Artemis-Q5_K_S.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/d3-mini-Artemis-GGUF. Download size is not runtime memory. Measured Q5_K_S: same answer as BF16 97.25%, 0 confident answers changed on the 160-case final set; protocol a100-620d222-20261025.
d3-mini decision model in GGUF, compressed by TurinTech with Artemis. Use the /v1/systemone endpoint, not chat. Recommended: d3-mini-Artemis-Q5_K_S.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/d3-mini-Artemis-GGUF. Download size is not runtime memory. Measured Q5_K_S: same answer as BF16 97.25%, 0 confident answers changed on the 160-case final set; protocol a100-620d222-20261025.