Tested: MiniMax H3 Runs Locally on 64GB MacBook Pro via Phosphene
cocktailpeanut · x · 2026-08-05
A developer has successfully run the MiniMax H3 model locally on a 64GB MacBook Pro using the Phosphene tool.
According to the test results, while the generation process works fine, running the model slows down the entire system due to the machine just meeting the 64GB minimum memory requirement.
More from Infra
- Best On-Device AI Models for 8GB RAM Phones Updated — Jasonio · 2026-08-05
- Energy Sovereignty Is the Prerequisite for AI Superpower Status — NinaDSchick · 2026-08-05
- The Great AI Repatriation: Why Hybrid is the Practical Future — DavidLinthicum · 2026-08-05
- Meta Scales Ads Recommendation Model to LLM Size, Doubling Training Efficiency — Meta_Engineers · 2026-08-05
- Valar Atomics Vision: Cheap Nuclear Energy to Power AI Robotics in Heavy Industry — johncoogan · 2026-08-05
- LMSYS Releases SpecForge Update: Advanced Speculative Decoding for Major Models — BanghuaZ · 2026-08-05