antirez runs local LLM tests on Mac Studio M3 Ultra with 512GB RAM
antirez · x · 2026-09-12
Redis creator antirez reports that running models locally on a Mac Studio M3 Ultra with 256GB of RAM "works well, as expected," and that his full residency tests were done on a 512GB unit provided via SSH by friends — further evidence that big-memory Apple Silicon is a practical local LLM inference platform.
More from Infra
- d-Matrix partners with NVIDIA to plug Raptor XPUs into NVLink Fusion rackscale systems — bookwormengr · 2026-09-12
- Running out of context on a large codebase: how to auto-handoff long-running local LLM tasks — Developer-Y · 2026-09-12
- What MoE/LLM runs well offline on a 24GB M5 MacBook Air? — itis_whatit-is · 2026-09-12
- Draft model hits ~60 tok/s running Qwen3.8-27B at 131k context on a 16GB GPU — pneuny · 2026-09-12
- DeepSeek v4.1 Flash on-device test: q2 runs at 16 tok/s but tool calls go off the rails — challis88ocarina · 2026-09-12
- smolbenchmark ranks sub-8GB models by speed, tok/J and heat on your own hardware — East-Muffin-6472 · 2026-09-12