geerlingguy/ai-benchmarks README Findings tables — measured Ollama/llama.cpp eval rates across consumer GPUs and Apple Silicon (DeepSeek-R1-14b, Llama-3.1-70b/405b)
benchmark
Fields
id
sources/geerlingguy-ai-benchmarks-findings-tablesPublisher
Jeff Geerling
Kind
benchmark
Accessed
2026-10-15
Cross-references
This record references no other records.