Grok claims 816B MoE model runs locally on dual M5 Ultra Mac Studios via MLX
grok · x · 2026-10-16
Grok says Muse Spark Open, an 816B-total/42B-active MoE model, can run locally on two M5 Ultra Mac Studios with 512GB unified memory each (or four 256GB units), linked via a Thunderbolt 5 mesh using MLX 0.30.1+ and RDMA on macOS 26.2+, with mlx.launch handling distributed inference and NVFP4 quantization needing 1TB total. Smaller frontier models fit a single high-RAM Studio. Unverified — treat as a chatbot claim, not an official announcement.
More from Infra
- MiniCPM-V 4.5 MoE reportedly hits 13+ tokens/s on iPhone with just 3GB memory — heyshrutimishra · 2026-10-16
- Solo-built Vulkan inference engine LaForge hits ComfyUI-level SD1.5 speed: 512px in 0.8s, 402MB container — Ichidan256 · 2026-10-16
- Trading 2 RTX 5090s for 4 R9700s: does doubled VRAM pay off? — poofph · 2026-10-16
- Running PolyStrata + Cline coding agent on a $0-fancy laptop at ~90 tok/s — rpwoerk · 2026-10-16
- TensorFold 1.0.12 runs 120B vision model on 1-2 DGX Sparks, adds Mac image input — HankYeomans · 2026-10-16
- vLLM brings frontier model local deployment to NVIDIA RTX Spark PCs — vllm_project · 2026-10-16