zml/llmd claims faster-than-oMLX Metal inference, adds NVFP4 support
jedisct1 · x · 2026-10-24
- Developer steeve reminds that zml's local inference engine llmd runs natively on Apple Metal and is claimed to be faster than oMLX, with new support for NVIDIA's NVFP4 quantization format.
- A new build (20261023.0) is available via Homebrew: brew upgrade zml/zml/llmd.
More from Infra
- Customers prepay billions for AI chip capacity: what the terms reveal about who wins — tengyanAI · 2026-10-24
- Nvidia pays multibillion-dollar advances to lock in substrate capacity through 2028, 2.5x in three years — tengyanAI · 2026-10-24
- Anthropic's binding payments estimated at $56bn in 2027, $86bn in 2028, covered by projected revenue — teortaxesTex · 2026-10-24
- Cutting 5.8s first-token latency on Orin Nano: short prompts, cached tool schemas — AIFlow_ML · 2026-10-24
- Cognitive Revolution: GPU credit crunch, 2027 RSI timelines, supply chain value — The Cognitive Revolution · 2026-10-24
- billion-context plugin compresses billion-token agent sessions into a 100K window — aigclink · 2026-10-24