LiquidAI ships MLX versions of d1 models optimized for Apple Silicon local inference
JosephJacks_ · x · 2026-10-13
LiquidAI released MLX-optimized versions of its d1 models on Hugging Face, including d1-omni-600M (8bit/fp16) and d1-3B (4bit/8bit/fp16) image-text-to-text models, runnable locally on Apple Silicon via mlx-vlm. The post also explains how decision models differ from traditional LLMs and advises benchmarking for the speed/quality tradeoff in your application.
More from Infra
- NVIDIA's LoGRA cuts RL training memory by 45.7%, using less than LoRA — omarsar0 · 2026-10-13
- The Neocloud Map: physical ownership vs platform depth are separate axes — AccBalanced · 2026-10-13
- Will compute trade like oil? GPU rental indexes show B300 down 8.5% — AccBalanced · 2026-10-13
- Ai2 ships Olmo-core 3 training framework scaling MoE LLMs past 1 trillion parameters — dl_weekly · 2026-10-13
- Liquid Inference serves ~2B tokens in first days, claims cheaper prices than 98% of OpenRouter traffic — AccBalanced · 2026-10-13
- Solo dev turns old laptops into free security guards with local LLMs via Observer — Roy3838 · 2026-10-13