{"slug":"graniet-llama-cpp","source_name":"graniet/llama-cpp","name":"Graniet/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":26.09,"pass_rate_pct":91.3,"total_cases":23,"passed_cases":21,"tokens_delta_pct":83.2,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-23T05:04:44.065504+00:00"},"skill_score":0.913,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":26.09,"with_pass_pct":91.3,"without_pass_pct":65.2,"tokens_delta_pct":83.2,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":23,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-23T05:04:44.065504+00:00","run_id":"708371b2-db18-4b10-aa1c-c91eda8e1f32","latest_attempt":{"id":"708371b2-db18-4b10-aa1c-c91eda8e1f32","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-08-23T05:04:44.065504+00:00","gate":null},"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,"total_uses":0,"total_users":0,"manifest_hash":"388c08bead8005f3621fd1dfbf6bee6a18c642174736d46a097efb26f059f846","install_name":"graniet-llama-cpp","version_id":"8e1089d6-bc69-4dfc-8625-4ed5961ed5cd","body_sha256":"388c08bead8005f3621fd1dfbf6bee6a18c642174736d46a097efb26f059f846","render_hash":"2daf0d8aeb192720602ebba09e409752bfec0e0779485724ee5876c67ab898dd","raw_url":"https://app.decimal.ai/s/graniet-llama-cpp/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/graniet-llama-cpp"}