Old Mac Pro still proving its worth
An old Mac Pro, originally costing nearly £10,000, is being repurposed for local LLM work thanks to new Linux drivers that enable its D700 GPUs. The machine, equipped with 64GB of RAM and 24 cores, can now run models via llama.cpp, achieving usable speeds for tasks like planning. Notably, the user found that Qwen 3.5 9B provided superior planning output compared to Anthropic's Claude Sonnet 4.6. AI
IMPACT Demonstrates that older, specialized hardware can still be viable for local LLM inference with software updates.