{"slug":"openlair-llama-cpp","source_name":"openlair/llama-cpp","name":"Openlair/Llama Cpp","description":"Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.","version":1,"lift":{"pass_rate_delta_pts":13.64,"pass_rate_pct":86.4,"total_cases":22,"passed_cases":19,"tokens_delta_pct":79.4,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-08T00:34:13.739759+00:00"},"skill_score":0.8636,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":13.64,"with_pass_pct":86.4,"without_pass_pct":72.7,"tokens_delta_pct":79.4,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-08T00:34:13.739759+00:00","run_id":"cd35766f-cb0e-4110-9bbf-775c91c45a19","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"076b3f04bde1c4b23788c8aed5ada7dedf89e953dec739983d70b5be51c2fbec","raw_url":"https://app.decimal.ai/s/openlair-llama-cpp/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/openlair-llama-cpp"}